[ { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-02-19", "cache_creation_input_token_cost_above_1hr": 0.000006, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "claude-3-7-sonnet-20250219", "model_name": "Claude 3 7 Sonnet (Feb 2025)", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "deprecation_date": "2026-06-15", "max_tokens": 32000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-4-opus-20250514", "model_name": "Claude 4 Opus (May 2025)", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "deprecation_date": "2026-06-15", "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_above_200k_tokens": 0.000006, "max_tokens": 64000, "output_cost_per_token_above_200k_tokens": 0.0000225, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-4-sonnet-20250514", "model_name": "Claude 4 Sonnet (May 2025)", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-10-15", "cache_creation_input_token_cost_above_1hr": 0.000002, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_native_structured_output": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 4096, "model_id": "claude-haiku-4-5-20251001", "model_name": "Claude Haiku 4 5 (Oct 2025)", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.00002, "max_tokens": 128000, "prompt_cache_min_tokens": 512, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://platform.claude.com/docs/en/about-claude/models/overview", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "provider_specific_entry": { "us": 1.1 }, "model_id": "claude-mythos-5", "model_name": "Claude Mythos 5", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-09-01", "cache_creation_input_token_cost_above_1hr": 0.00002, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "prompt_cache_min_tokens": 512, "supports_native_structured_output": true, "source": "https://platform.claude.com/docs/en/models/mythos-5-1/overview", "model_id": "claude-mythos-5-1", "model_name": "Claude Mythos 5 1", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.00002, "max_tokens": 128000, "prompt_cache_min_tokens": 512, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://platform.claude.com/docs/en/about-claude/models/overview", "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "provider_specific_entry": { "us": 1.1 }, "model_id": "claude-mythos-preview", "model_name": "Claude Mythos Preview", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "deprecation_date": "2026-08-05", "cache_creation_input_token_cost_above_1hr": 0.00003, "max_tokens": 32000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-opus-4-1-20250805", "model_name": "Claude Opus 4 1 (Aug 2025)", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "deprecation_date": "2026-06-15", "cache_creation_input_token_cost_above_1hr": 0.00003, "max_tokens": 32000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-opus-4-20250514", "model_name": "Claude 4 Opus", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-11-24", "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096, "model_id": "claude-opus-4-5-20251101", "model_name": "Claude Opus 4 5 (Nov 2025)", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-02-05", "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "provider_specific_entry": { "us": 1.1 }, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_speed": true, "prompt_cache_min_tokens": 4096, "model_id": "claude-opus-4-6-20260205", "model_name": "Claude Opus 4 6 (Feb 2026)", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-04-16", "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "provider_specific_entry": { "us": 1.1 }, "supports_output_config": true, "supports_speed": true, "prompt_cache_min_tokens": 2048, "model_id": "claude-opus-4-7-20260416", "model_name": "Claude Opus 4 7 (Apr 2026)", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "deprecation_date": "2026-06-15", "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-sonnet-4-20250514", "model_name": "Claude 4 Sonnet", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-09-29", "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_web_search": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-sonnet-4-5-20250929", "model_name": "Claude Sonnet 4 5 (Sep 2025)", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-12-05", "supports_mid_conversation_system": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost_above_1hr": 0.00002, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "model_id": "azure_ai/claude-fable-5", "model_name": "Claude Fable 5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-12-05", "supports_mid_conversation_system": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost_above_1hr": 0.00002, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "model_id": "azure_ai/claude-fable-5-1", "model_name": "Claude Fable 5 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-10-19", "cache_creation_input_token_cost_above_1hr": 0.000002, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 4096, "model_id": "azure_ai/claude-haiku-4-5", "model_name": "Claude Haiku 4 5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "deprecation_date": "2026-08-05", "cache_creation_input_token_cost_above_1hr": 0.00003, "max_tokens": 32000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "azure_ai/claude-opus-4-1", "model_name": "Claude Opus 4 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-10-19", "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096, "model_id": "azure_ai/claude-opus-4-5", "model_name": "Claude Opus 4 5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-02-02", "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost_above_1hr": 0.00001, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 4096, "model_id": "azure_ai/claude-opus-4-6", "model_name": "Claude Opus 4 6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-04-06", "supports_adaptive_thinking": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost_above_1hr": 0.00001, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 2048, "model_id": "azure_ai/claude-opus-4-7", "model_name": "Claude Opus 4 7", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-09-01", "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost_above_1hr": 0.00001, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 1024, "model_id": "azure_ai/claude-opus-4-8", "model_name": "Claude Opus 4 8", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-07-08", "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost_above_1hr": 0.00001, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "model_id": "azure_ai/claude-opus-5", "model_name": "Claude Opus 5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-10-19", "cache_creation_input_token_cost_above_1hr": 0.000006, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "azure_ai/claude-sonnet-4-5", "model_name": "Claude Sonnet 4 5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "deprecation_date": "2027-02-10", "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000006, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_output_config": true, "prompt_cache_min_tokens": 1024, "model_id": "azure_ai/claude-sonnet-4-6", "model_name": "Claude Sonnet 4 6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-06-30", "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.000004, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 1024, "model_id": "azure_ai/claude-sonnet-5", "model_name": "Claude Sonnet 5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000006, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-15", "max_tokens": 100000, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure_ai/codex-mini", "model_name": "Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.5, "output_cost_per_million": 6, "cache_read_cost_per_token": 3.75e-7, "cache_read_cost_per_million": 0.375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054, "max_input_tokens": 128000, "max_output_tokens": 8192, "deprecation_date": "2026-08-13", "max_tokens": 8192, "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/deepseek-r1", "model_name": "DeepSeek R1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.35, "output_cost_per_million": 5.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000123, "output_cost_per_token": 0.00000494, "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecation_date": "2026-07-13", "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/deepseek-v3.1", "model_name": "Deepseek V3.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.23, "output_cost_per_million": 4.94, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5.8e-7, "output_cost_per_token": 0.00000168, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/deepseek-v3.2", "model_name": "Deepseek V3.2", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.58, "output_cost_per_million": 1.68, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5.8e-7, "output_cost_per_token": 0.00000168, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/deepseek-v3.2-speciale", "model_name": "Deepseek V3.2 Speciale", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.58, "output_cost_per_million": 1.68, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.9e-7, "output_cost_per_token": 5.1e-7, "max_input_tokens": 1000000, "max_output_tokens": 384000, "deprecation_date": "2028-02-20", "max_tokens": 384000, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", "supports_reasoning": true, "supports_tool_choice": true, "supports_prompt_caching": true, "model_id": "azure_ai/deepseek-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19, "output_cost_per_million": 0.51, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4.4e-7, "output_cost_per_token": 0.00000132, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2026-12-03", "max_tokens": 128000, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/DeepSeek-V4-Flash-0731", "model_name": "DeepSeek V4 Flash 0731", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.44, "output_cost_per_million": 1.32, "cache_read_cost_per_token": 1.4e-8, "cache_read_cost_per_million": 0.014, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000174, "output_cost_per_token": 0.00000348, "max_input_tokens": 1000000, "max_output_tokens": 384000, "deprecation_date": "2028-02-20", "max_tokens": 384000, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", "supports_reasoning": true, "supports_tool_choice": true, "supports_prompt_caching": true, "model_id": "azure_ai/deepseek-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.74, "output_cost_per_million": 3.48, "cache_read_cost_per_token": 1.45e-7, "cache_read_cost_per_million": 0.145, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6.2e-7, "output_cost_per_token": 0.00000185, "max_input_tokens": 163840, "max_output_tokens": 163840, "deprecation_date": "2027-07-01", "max_tokens": 163840, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-DeepSeek-V3.2", "model_name": "FW DeepSeek V3.2", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.62, "output_cost_per_million": 1.85, "cache_read_cost_per_token": 3.1e-7, "cache_read_cost_per_million": 0.31, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001925, "output_cost_per_token": 0.000003828, "max_input_tokens": 1000000, "max_output_tokens": 384000, "max_tokens": 384000, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-DeepSeek-V4-Pro", "model_name": "FW DeepSeek V4 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.9250000000000003, "output_cost_per_million": 3.8279999999999994, "cache_read_cost_per_token": 1.65e-7, "cache_read_cost_per_million": 0.165, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.00000352, "max_input_tokens": 200000, "max_output_tokens": 128000, "deprecation_date": "2027-07-01", "max_tokens": 128000, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-GLM-5", "model_name": "FW GLM 5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1, "output_cost_per_million": 3.52, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000154, "output_cost_per_token": 0.00000484, "max_input_tokens": 202800, "max_output_tokens": 131072, "deprecation_date": "2027-07-01", "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-GLM-5.1", "model_name": "FW GLM 5.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.54, "output_cost_per_million": 4.84, "cache_read_cost_per_token": 2.86e-7, "cache_read_cost_per_million": 0.286, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000154, "output_cost_per_token": 0.00000484, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-GLM-5.2", "model_name": "FW GLM 5.2", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.54, "output_cost_per_million": 4.84, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000021, "output_cost_per_token": 0.0000066, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-GLM-5.2-Fast", "model_name": "FW GLM 5.2 Fast", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.0999999999999996, "output_cost_per_million": 6.6000000000000005, "cache_read_cost_per_token": 2.1e-7, "cache_read_cost_per_million": 0.21, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.00000405, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "source": "https://fireworks.ai/models/fireworks/inkling", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-Inkling", "model_name": "FW Inkling", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1, "output_cost_per_million": 4.05, "cache_read_cost_per_token": 1.7e-7, "cache_read_cost_per_million": 0.16999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 6.6e-7, "output_cost_per_token": 0.0000033, "max_input_tokens": 262144, "max_output_tokens": 262144, "deprecation_date": "2027-07-01", "max_tokens": 262144, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-Kimi-K2.5", "model_name": "FW Kimi K2.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.66, "output_cost_per_million": 3.3000000000000003, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000001045, "output_cost_per_token": 0.0000044, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-Kimi-K2.6", "model_name": "FW Kimi K2.6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.045, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 1.76e-7, "cache_read_cost_per_million": 0.176, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000105, "output_cost_per_token": 0.0000044, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-Kimi-K2.7-Code", "model_name": "FW Kimi K2.7 Code", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.0499999999999998, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.1e-7, "cache_read_cost_per_million": 0.21, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k3-through-fireworks-ai-on-microsoft-foundry/4540187", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-Kimi-K3", "model_name": "FW Kimi K3", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3.3e-7, "output_cost_per_token": 0.00000132, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "deprecation_date": "2027-07-01", "max_tokens": 1000000, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-MiniMax-M2.5", "model_name": "FW MiniMax M2.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.33, "output_cost_per_million": 1.32, "cache_read_cost_per_token": 3.3e-8, "cache_read_cost_per_million": 0.032999999999999995, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 3.3e-7, "output_cost_per_token": 0.00000132, "max_input_tokens": 512000, "max_output_tokens": 512000, "max_tokens": 512000, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-MiniMax-M3", "model_name": "FW MiniMax M3", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.33, "output_cost_per_million": 1.32, "cache_read_cost_per_token": 6.6e-8, "cache_read_cost_per_million": 0.06599999999999999, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://fireworks.ai/models/fireworks/nemotron-3-ultra-nvfp4", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-Nemotron-3-Ultra-NVFP4", "model_name": "FW Nemotron 3 Ultra NVFP4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 1.19e-7, "cache_read_cost_per_million": 0.119, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 6e-8, "output_cost_per_token": 2.2e-7, "max_input_tokens": 262144, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B", "model_name": "FW Nemotron Lightning 3.5 30B A3B", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.06, "output_cost_per_million": 0.22, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000127, "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecation_date": "2026-05-01", "max_tokens": 131072, "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/global/grok-3-mini", "model_name": "Grok 3 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 1.27, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-09-02", "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045, "source": "https://ai.azure.com/catalog/models/gpt-5.4", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure_ai/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 15, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-09-02", "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045, "source": "https://ai.azure.com/catalog/models/gpt-5.4", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure_ai/gpt-5.4-2026-03-05", "model_name": "GPT-5.4 (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 15, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token_priority": 0.0000015, "max_tokens": 128000, "output_cost_per_token_priority": 0.000009, "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure_ai/gpt-5.4-mini", "model_name": "GPT-5.4 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token_priority": 0.0000015, "max_tokens": 128000, "output_cost_per_token_priority": 0.000009, "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure_ai/gpt-5.4-mini-2026-03-17", "model_name": "GPT-5.4 Mini (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "cache_read_input_token_cost_priority": 4e-8, "input_cost_per_token_priority": 4e-7, "max_tokens": 128000, "output_cost_per_token_priority": 0.0000025, "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure_ai/gpt-5.4-nano", "model_name": "GPT-5.4 Nano", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "cache_read_input_token_cost_priority": 4e-8, "input_cost_per_token_priority": 4e-7, "max_tokens": 128000, "output_cost_per_token_priority": 0.0000025, "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure_ai/gpt-5.4-nano-2026-03-17", "model_name": "GPT-5.4 Nano (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-09-07", "cache_read_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_priority": 0.000006, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000012, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_priority": 0.00006, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_priority": 0.00036, "output_cost_per_token_above_272k_tokens_priority": 0.00054, "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure_ai/gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-09-07", "cache_read_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_priority": 0.000006, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000012, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_priority": 0.00006, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_priority": 0.00036, "output_cost_per_token_above_272k_tokens_priority": 0.00054, "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure_ai/gpt-5.4-pro-2026-03-05", "model_name": "GPT-5.4 Pro (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "source": "https://ai.azure.com/catalog/models/gpt-5.5", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure_ai/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "source": "https://ai.azure.com/catalog/models/gpt-5.5", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure_ai/gpt-5.5-2026-04-23", "model_name": "GPT-5.5 (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000025, "cache_read_input_token_cost_above_272k_tokens": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://ai.azure.com/catalog/models/gpt-6-astra", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "azure_ai/gpt-6-astra", "model_name": "GPT-6 Astra", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-12-02", "max_tokens": 128000, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/gpt-chat-latest", "model_name": "GPT Chat Latest", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000127, "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecation_date": "2026-05-01", "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-3-mini", "model_name": "Grok 3 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 1.27, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4-1-fast-reasoning", "model_name": "Grok 4 1 Fast Reasoning", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 262000, "max_output_tokens": 8192, "deprecation_date": "2027-04-06", "max_tokens": 8192, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_tool_choice": true, "supports_web_search": true, "supports_reasoning": true, "model_id": "azure_ai/grok-4-20-reasoning", "model_name": "Grok 4 20 Reasoning", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-grok-4-3-on-microsoft-foundry-latest-generation-agentic-capabilities/4517096", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4.3", "model_name": "Grok 4.3", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/grok-4-6-comes-to-microsoft-foundry-models-built-for-long-horizon-reasoning-and-/4547578", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4.6", "model_name": "Grok 4.6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 262144, "deprecation_date": "2027-04-16", "max_tokens": 262144, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "supports_prompt_caching": true, "model_id": "azure_ai/kimi-k2.6", "model_name": "Kimi K2.6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.6e-7, "cache_read_cost_per_million": 0.16, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 262144, "deprecation_date": "2026-10-03", "max_tokens": 262144, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/kimi-k2.7-code", "model_name": "Kimi K2.7 Code", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.9e-7, "cache_read_cost_per_million": 0.19, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/MAI-DS-R1", "model_name": "MAI DS R1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.35, "output_cost_per_million": 5.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 256000, "max_output_tokens": 64000, "max_tokens": 64000, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/MAI-Thinking-1", "model_name": "MAI Thinking 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.25e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "azure_ai/Phi-4-reasoning", "model_name": "Phi 4 Reasoning", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.125, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000006, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-15", "max_tokens": 100000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/codex-mini", "model_name": "Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.5, "output_cost_per_million": 6, "cache_read_cost_per_token": 3.75e-7, "cache_read_cost_per_million": 0.375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000012, "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": false, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/computer-use-preview", "model_name": "Computer Use Preview", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "output_cost_per_million": 12, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001375, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-02-09", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5-2025-08-07", "model_name": "GPT-5 (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.375, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.375e-7, "cache_read_cost_per_million": 0.1375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-02-09", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5-mini-2025-08-07", "model_name": "GPT-5 Mini (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.275, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 2.75e-8, "cache_read_cost_per_million": 0.0275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5.5e-8, "output_cost_per_token": 4.4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-02-09", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5-nano-2025-08-07", "model_name": "GPT-5 Nano (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.055, "output_cost_per_million": 0.44, "cache_read_cost_per_token": 5.5e-9, "cache_read_cost_per_million": 0.0055, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "model_id": "azure/eu/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 128000, "deprecation_date": "2026-06-29", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "model_id": "azure/eu/gpt-5.1-chat", "model_name": "GPT-5.1 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.275, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.0000165, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-09-02", "cache_read_input_token_cost_priority": 5.5e-7, "input_cost_per_token_priority": 0.0000055, "output_cost_per_token_priority": 0.000033, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure/eu/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.0000165, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-09-02", "cache_read_input_token_cost_priority": 5.5e-7, "input_cost_per_token_priority": 0.0000055, "output_cost_per_token_priority": 0.000033, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure/eu/gpt-5.4-2026-03-05", "model_name": "GPT-5.4 (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_priority": 0.00000138, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/eu/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_priority": 0.00000138, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/eu/gpt-5.5-2026-04-23", "model_name": "GPT-5.5 (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00001375, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.0000275, "cache_creation_input_token_cost_priority": 0.00001375, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000022, "cache_read_input_token_cost_priority": 0.0000011, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_above_272k_tokens_priority": 0.000022, "input_cost_per_token_priority": 0.000011, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_above_272k_tokens_priority": 0.000099, "output_cost_per_token_priority": 0.000066, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/eu/gpt-5.6", "model_name": "GPT-5.6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 0.00000132, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 5.5e-7, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.0000011, "cache_creation_input_token_cost_priority": 5.5e-7, "cache_read_input_token_cost_above_272k_tokens": 4.4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-8, "cache_read_input_token_cost_priority": 4.4e-8, "input_cost_per_token_above_272k_tokens": 4.4e-7, "input_cost_per_token_above_272k_tokens_priority": 8.8e-7, "input_cost_per_token_priority": 4.4e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00000198, "output_cost_per_token_above_272k_tokens_priority": 0.00000396, "output_cost_per_token_priority": 0.00000264, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/eu/gpt-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.22, "output_cost_per_million": 1.32, "cache_read_cost_per_token": 2.2e-8, "cache_read_cost_per_million": 0.022, "cache_write_cost_per_token": 2.75e-7, "cache_write_cost_per_million": 0.275, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.00001375, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.0000275, "cache_creation_input_token_cost_priority": 0.00001375, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000022, "cache_read_input_token_cost_priority": 0.0000011, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_above_272k_tokens_priority": 0.000022, "input_cost_per_token_priority": 0.000011, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_above_272k_tokens_priority": 0.000099, "output_cost_per_token_priority": 0.000066, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/eu/gpt-5.6-sol", "model_name": "GPT-5.6 Sol", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.0000132, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.0000055, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000011, "cache_creation_input_token_cost_priority": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 4.4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-7, "cache_read_input_token_cost_priority": 4.4e-7, "input_cost_per_token_above_272k_tokens": 0.0000044, "input_cost_per_token_above_272k_tokens_priority": 0.0000088, "input_cost_per_token_priority": 0.0000044, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000198, "output_cost_per_token_above_272k_tokens_priority": 0.0000396, "output_cost_per_token_priority": 0.0000264, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/eu/gpt-5.6-terra", "model_name": "GPT-5.6 Terra", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.2, "output_cost_per_million": 13.200000000000001, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_vision": false, "input_cost_per_token": 0.00000121, "output_cost_per_token": 0.00000484, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "input_cost_per_token_batches": 6.05e-7, "max_tokens": 100000, "output_cost_per_token_batches": 0.00000242, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/eu/o3-mini-2025-01-31", "model_name": "o3 mini (Jan 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.21, "output_cost_per_million": 4.84, "cache_read_cost_per_token": 6.05e-7, "cache_read_cost_per_million": 0.605, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "model_id": "azure/global/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 128000, "deprecation_date": "2026-06-29", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "model_id": "azure/global/gpt-5.1-chat", "model_name": "GPT-5.1 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/global/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/global/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-02-09", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5", "model_name": "GPT-5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-02-09", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-2025-08-07", "model_name": "GPT-5 (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-06-29", "max_tokens": 16384, "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-chat", "model_name": "GPT-5 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-06-29", "max_tokens": 16384, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-chat-latest", "model_name": "GPT-5 Chat Latest", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-03-17", "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-codex", "model_name": "GPT-5 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-02-09", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-mini", "model_name": "GPT-5 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-02-09", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-mini-2025-08-07", "model_name": "GPT-5 Mini (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-02-09", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-nano", "model_name": "GPT-5 Nano", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 5e-9, "cache_read_cost_per_million": 0.005, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-02-09", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-nano-2025-08-07", "model_name": "GPT-5 Nano (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 5e-9, "cache_read_cost_per_million": 0.005, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00012, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-04-07", "max_tokens": 128000, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-pro", "model_name": "GPT-5 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 15, "output_cost_per_million": 120, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "model_id": "azure/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_minimal_reasoning_effort": true, "model_id": "azure/gpt-5.1-2025-11-13", "model_name": "GPT-5.1 (Nov 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 128000, "deprecation_date": "2026-06-29", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "model_id": "azure/gpt-5.1-chat", "model_name": "GPT-5.1 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-06-29", "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 16384, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "model_id": "azure/gpt-5.1-chat-2025-11-13", "model_name": "GPT-5.1 Chat (Nov 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-2025-11-13", "model_name": "GPT-5.1 Codex (Nov 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-18", "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-max", "model_name": "GPT-5.1 Codex Max", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 128000, "output_cost_per_token_priority": 0.0000036, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-mini-2025-11-13", "model_name": "GPT-5.1 Codex Mini (Nov 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-06-08", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.2", "model_name": "GPT-5.2", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-06-08", "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 128000, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.2-2025-12-11", "model_name": "GPT-5.2 (Dec 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-06-29", "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 16384, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.2-chat", "model_name": "GPT-5.2 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-05-13", "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 16384, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.2-chat-2025-12-11", "model_name": "GPT-5.2 Chat (Dec 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-07-13", "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.2-codex", "model_name": "GPT-5.2 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.2-pro", "model_name": "GPT-5.2 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 21, "output_cost_per_million": 168, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.2-pro-2025-12-11", "model_name": "GPT-5.2 Pro (Dec 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 21, "output_cost_per_million": 168, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-06-29", "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 16384, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.3-chat", "model_name": "GPT-5.3 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-08-24", "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.3-codex", "model_name": "GPT-5.3 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-09-02", "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 15, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-09-02", "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure/gpt-5.4-2026-03-05", "model_name": "GPT-5.4 (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 15, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "model_id": "azure/gpt-5.4-mini", "model_name": "GPT-5.4 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "model_id": "azure/gpt-5.4-mini-2026-03-17", "model_name": "GPT-5.4 Mini (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "model_id": "azure/gpt-5.4-nano", "model_name": "GPT-5.4 Nano", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "model_id": "azure/gpt-5.4-nano-2026-03-17", "model_name": "GPT-5.4 Nano (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-09-07", "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-09-07", "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.4-pro-2026-03-05", "model_name": "GPT-5.4 Pro (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.5-2026-04-23", "model_name": "GPT-5.5 (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false, "model_id": "azure/gpt-5.5-pro", "model_name": "GPT-5.5 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.5-pro-2026-04-23", "model_name": "GPT-5.5 Pro (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.0000125, "cache_creation_input_token_cost_priority": 0.0000125, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000025, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/gpt-5.6", "model_name": "GPT-5.6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 5e-7, "cache_creation_input_token_cost_priority": 5e-7, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "cache_read_input_token_cost_priority": 4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, "input_cost_per_token_above_272k_tokens": 4e-7, "input_cost_per_token_priority": 4e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000018, "output_cost_per_token_priority": 0.0000024, "output_cost_per_token_above_272k_tokens_priority": 0.0000036, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/gpt-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 2.5e-7, "cache_write_cost_per_million": 0.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.0000125, "cache_creation_input_token_cost_priority": 0.0000125, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000025, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/gpt-5.6-sol", "model_name": "GPT-5.6 Sol", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_creation_input_token_cost_priority": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00001, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "cache_read_input_token_cost_priority": 4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "input_cost_per_token_priority": 0.000004, "input_cost_per_token_above_272k_tokens_priority": 0.000008, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000018, "output_cost_per_token_priority": 0.000024, "output_cost_per_token_above_272k_tokens_priority": 0.000036, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/gpt-5.6-terra", "model_name": "GPT-5.6 Terra", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000025, "cache_read_input_token_cost_above_272k_tokens": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "azure/gpt-6-astra", "model_name": "GPT-6 Astra", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o1", "model_name": "o1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 15, "output_cost_per_million": 60, "cache_read_cost_per_token": 0.0000075, "cache_read_cost_per_million": 7.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o1-2024-12-17", "model_name": "o1 (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 15, "output_cost_per_million": 60, "cache_read_cost_per_token": 0.0000075, "cache_read_cost_per_million": 7.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.00000121, "output_cost_per_token": 0.00000484, "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "supports_prompt_caching": true, "supports_reasoning": true, "model_id": "azure/o1-mini", "model_name": "o1 mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.21, "output_cost_per_million": 4.84, "cache_read_cost_per_token": 6.05e-7, "cache_read_cost_per_million": 0.605, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "supports_prompt_caching": true, "supports_reasoning": true, "model_id": "azure/o1-mini-2024-09-12", "model_name": "o1 mini (Sep 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "supports_prompt_caching": true, "supports_reasoning": true, "model_id": "azure/o1-preview", "model_name": "o1 Preview", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 15, "output_cost_per_million": 60, "cache_read_cost_per_token": 0.0000075, "cache_read_cost_per_million": 7.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "model_id": "azure/o1-preview-2024-09-12", "model_name": "o1 Preview (Sep 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 15, "output_cost_per_million": 60, "cache_read_cost_per_token": 0.0000075, "cache_read_cost_per_million": 7.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "max_tokens": 100000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o3", "model_name": "o3", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "max_tokens": 100000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o3-2025-04-16", "model_name": "o3 (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00004, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "max_tokens": 100000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/o3-deep-research", "model_name": "O3 Deep Research", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 40, "cache_read_cost_per_token": 0.0000025, "cache_read_cost_per_million": 2.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o3-mini", "model_name": "o3 mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_function_calling": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o3-mini-2025-01-31", "model_name": "o3 mini (Jan 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00002, "output_cost_per_token": 0.00008, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "input_cost_per_token_batches": 0.00001, "max_tokens": 100000, "output_cost_per_token_batches": 0.00004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o3-pro", "model_name": "o3 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 20, "output_cost_per_million": 80, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00002, "output_cost_per_token": 0.00008, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "input_cost_per_token_batches": 0.00001, "max_tokens": 100000, "output_cost_per_token_batches": 0.00004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o3-pro-2025-06-10", "model_name": "o3 Pro (Jun 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 20, "output_cost_per_million": 80, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "max_tokens": 100000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o4-mini", "model_name": "o4 mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.75e-7, "cache_read_cost_per_million": 0.275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o4-mini-2025-04-16", "model_name": "o4 mini (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.75e-7, "cache_read_cost_per_million": 0.275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000171875, "output_cost_per_token": 0.00001375, "max_input_tokens": 272000, "max_output_tokens": 128000, "default_reasoning_effort": "none", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us-gov/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.71875, "output_cost_per_million": 13.75, "cache_read_cost_per_token": 1.71875e-7, "cache_read_cost_per_million": 0.171875, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.000001513, "output_cost_per_token": 0.00000605, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/us-gov/o3-mini", "model_name": "o3 mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.513, "output_cost_per_million": 6.05, "cache_read_cost_per_token": 7.57e-7, "cache_read_cost_per_million": 0.757, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_function_calling": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001375, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-02-09", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-5-2025-08-07", "model_name": "GPT-5 (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.375, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.375e-7, "cache_read_cost_per_million": 0.1375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-02-09", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-5-mini-2025-08-07", "model_name": "GPT-5 Mini (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.275, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 2.75e-8, "cache_read_cost_per_million": 0.0275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5.5e-8, "output_cost_per_token": 4.4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-02-09", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-5-nano-2025-08-07", "model_name": "GPT-5 Nano (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.055, "output_cost_per_million": 0.44, "cache_read_cost_per_token": 5.5e-9, "cache_read_cost_per_million": 0.0055, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "model_id": "azure/us/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 128000, "deprecation_date": "2026-06-29", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "model_id": "azure/us/gpt-5.1-chat", "model_name": "GPT-5.1 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/us/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/us/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.275, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.0000165, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-09-02", "cache_read_input_token_cost_priority": 5.5e-7, "input_cost_per_token_priority": 0.0000055, "output_cost_per_token_priority": 0.000033, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure/us/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.0000165, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-09-02", "cache_read_input_token_cost_priority": 5.5e-7, "input_cost_per_token_priority": 0.0000055, "output_cost_per_token_priority": 0.000033, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure/us/gpt-5.4-2026-03-05", "model_name": "GPT-5.4 (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_priority": 0.00000138, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/us/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_priority": 0.00000138, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/us/gpt-5.5-2026-04-23", "model_name": "GPT-5.5 (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00001375, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.0000275, "cache_creation_input_token_cost_priority": 0.00001375, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000022, "cache_read_input_token_cost_priority": 0.0000011, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_above_272k_tokens_priority": 0.000022, "input_cost_per_token_priority": 0.000011, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_above_272k_tokens_priority": 0.000099, "output_cost_per_token_priority": 0.000066, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/us/gpt-5.6", "model_name": "GPT-5.6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 0.00000132, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 5.5e-7, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.0000011, "cache_creation_input_token_cost_priority": 5.5e-7, "cache_read_input_token_cost_above_272k_tokens": 4.4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-8, "cache_read_input_token_cost_priority": 4.4e-8, "input_cost_per_token_above_272k_tokens": 4.4e-7, "input_cost_per_token_above_272k_tokens_priority": 8.8e-7, "input_cost_per_token_priority": 4.4e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00000198, "output_cost_per_token_above_272k_tokens_priority": 0.00000396, "output_cost_per_token_priority": 0.00000264, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/us/gpt-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.22, "output_cost_per_million": 1.32, "cache_read_cost_per_token": 2.2e-8, "cache_read_cost_per_million": 0.022, "cache_write_cost_per_token": 2.75e-7, "cache_write_cost_per_million": 0.275, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.00001375, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.0000275, "cache_creation_input_token_cost_priority": 0.00001375, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000022, "cache_read_input_token_cost_priority": 0.0000011, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_above_272k_tokens_priority": 0.000022, "input_cost_per_token_priority": 0.000011, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_above_272k_tokens_priority": 0.000099, "output_cost_per_token_priority": 0.000066, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/us/gpt-5.6-sol", "model_name": "GPT-5.6 Sol", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.0000132, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.0000055, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000011, "cache_creation_input_token_cost_priority": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 4.4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-7, "cache_read_input_token_cost_priority": 4.4e-7, "input_cost_per_token_above_272k_tokens": 0.0000044, "input_cost_per_token_above_272k_tokens_priority": 0.0000088, "input_cost_per_token_priority": 0.0000044, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000198, "output_cost_per_token_above_272k_tokens_priority": 0.0000396, "output_cost_per_token_priority": 0.0000264, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/us/gpt-5.6-terra", "model_name": "GPT-5.6 Terra", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.2, "output_cost_per_million": 13.200000000000001, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000011, "output_cost_per_token": 0.000055, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.0000275, "cache_read_input_token_cost_above_272k_tokens": 0.0000022, "input_cost_per_token_above_272k_tokens": 0.000022, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000825, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "azure/us/gpt-6-astra", "model_name": "GPT-6 Astra", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 11, "output_cost_per_million": 55, "cache_read_cost_per_token": 0.0000011, "cache_read_cost_per_million": 1.1, "cache_write_cost_per_token": 0.00001375, "cache_write_cost_per_million": 13.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.0000088, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "max_tokens": 100000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/us/o3-2025-04-16", "model_name": "o3 (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.2, "output_cost_per_million": 8.8, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 0.00000121, "output_cost_per_token": 0.00000484, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "input_cost_per_token_batches": 6.05e-7, "max_tokens": 100000, "output_cost_per_token_batches": 0.00000242, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/us/o3-mini-2025-01-31", "model_name": "o3 mini (Jan 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.21, "output_cost_per_million": 4.84, "cache_read_cost_per_token": 6.05e-7, "cache_read_cost_per_million": 0.605, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000121, "output_cost_per_token": 0.00000484, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/us/o4-mini-2025-04-16", "model_name": "o4 mini (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.21, "output_cost_per_million": 4.84, "cache_read_cost_per_token": 3.1e-7, "cache_read_cost_per_million": 0.31, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "model_id": "amazon.nova-2-lite-v1:0", "model_name": "Nova 2 Lite", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000021875, "output_cost_per_token": 0.0000175, "max_input_tokens": 1000000, "max_output_tokens": 64000, "input_cost_per_image_token": 0.0000021875, "input_cost_per_audio_token": 0.0000021875, "max_tokens": 64000, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "model_id": "amazon.nova-2-pro-preview-20251202-v1:0", "model_name": "Nova 2 Pro Preview (Dec 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.1875, "output_cost_per_million": 17.5, "cache_read_cost_per_token": 5.46875e-7, "cache_read_cost_per_million": 0.546875, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000036, "output_cost_per_token": 0.000018, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "anthropic.claude-3-7-sonnet-20240620-v1:0", "model_name": "Claude 3 7 Sonnet (Jun 2024)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.5999999999999996, "output_cost_per_million": 18, "cache_read_cost_per_token": 3.6e-7, "cache_read_cost_per_million": 0.36, "cache_write_cost_per_token": 0.0000045, "cache_write_cost_per_million": 4.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "anthropic.claude-3-7-sonnet-20250219-v1:0", "model_name": "Claude 3 7 Sonnet (Feb 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.00002, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "anthropic.claude-fable-5", "model_name": "Claude Fable 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.00002, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "anthropic.claude-fable-5-1", "model_name": "Claude Fable 5 1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000002, "supports_tool_search": true, "max_tokens": 64000, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-7, "output_cost_per_token_batches": 0.0000025, "model_id": "anthropic.claude-haiku-4-5-20251001-v1:0", "model_name": "Claude Haiku 4 5 (Oct 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000002, "supports_tool_search": true, "max_tokens": 64000, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_streaming": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "model_id": "anthropic.claude-haiku-4-5@20251001", "model_name": "Claude Haiku 4 5@ (Oct 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "thinking_always_on": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "model_id": "anthropic.claude-mythos-preview", "model_name": "Claude Mythos Preview", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "deprecation_date": "2027-01-08", "max_tokens": 32000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "anthropic.claude-opus-4-1-20250805-v1:0", "model_name": "Claude Opus 4 1 (Aug 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "anthropic.claude-opus-4-20250514-v1:0", "model_name": "Claude Opus 4 (May 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.00001, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "model_id": "anthropic.claude-opus-4-5-20251101-v1:0", "model_name": "Claude Opus 4 5 (Nov 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "supports_tool_search": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "model_id": "anthropic.claude-opus-4-6-v1", "model_name": "Claude Opus 4 6 V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "supports_tool_search": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, "model_id": "anthropic.claude-opus-4-7", "model_name": "Claude Opus 4 7", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "anthropic.claude-opus-4-8", "model_name": "Claude Opus 4 8", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "anthropic.claude-opus-5", "model_name": "Claude Opus 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "deprecation_date": "2026-10-14", "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, "model_id": "anthropic.claude-sonnet-4-20250514-v1:0", "model_name": "Claude Sonnet 4 (May 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 0.0000015, "output_cost_per_token_batches": 0.0000075, "model_id": "anthropic.claude-sonnet-4-5-20250929-v1:0", "model_name": "Claude Sonnet 4 5 (Sep 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000006, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "anthropic.claude-sonnet-4-6", "model_name": "Claude Sonnet 4 6", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost_above_1hr": 0.000004, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "anthropic.claude-sonnet-5", "model_name": "Claude Sonnet 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.4e-7, "output_cost_per_token": 0.00000222, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "ap-northeast-1/deepseek.v3.2", "model_name": "Deepseek.v3.2", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.74, "output_cost_per_million": 2.2199999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ap-northeast-1/minimax.minimax-m2.5", "model_name": "Minimax.minimax M2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.36, "output_cost_per_million": 1.44, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.3e-7, "output_cost_per_token": 0.00000303, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "model_id": "ap-northeast-1/moonshotai.kimi-k2-thinking", "model_name": "Moonshotai.kimi K2 Thinking", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.73, "output_cost_per_million": 3.03, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.4e-7, "output_cost_per_token": 0.00000222, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "ap-south-1/deepseek.v3.2", "model_name": "Deepseek.v3.2", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.74, "output_cost_per_million": 2.2199999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ap-south-1/minimax.minimax-m2.5", "model_name": "Minimax.minimax M2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.36, "output_cost_per_million": 1.44, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.1e-7, "output_cost_per_token": 0.00000294, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "model_id": "ap-south-1/moonshotai.kimi-k2-thinking", "model_name": "Moonshotai.kimi K2 Thinking", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.71, "output_cost_per_million": 2.94, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3.09e-7, "output_cost_per_token": 0.000001236, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ap-southeast-2/minimax.minimax-m2.5", "model_name": "Minimax.minimax M2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.309, "output_cost_per_million": 1.236, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.4e-7, "output_cost_per_token": 0.00000222, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "ap-southeast-3/deepseek.v3.2", "model_name": "Deepseek.v3.2", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.74, "output_cost_per_million": 2.2199999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ap-southeast-3/minimax.minimax-m2.5", "model_name": "Minimax.minimax M2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.36, "output_cost_per_million": 1.44, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3.3e-7, "output_cost_per_token": 0.00000275, "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "model_id": "apac.amazon.nova-2-lite-v1:0", "model_name": "Nova 2 Lite", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.33, "output_cost_per_million": 2.75, "cache_read_cost_per_token": 8.25e-8, "cache_read_cost_per_million": 0.0825, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000021875, "output_cost_per_token": 0.0000175, "max_input_tokens": 1000000, "max_output_tokens": 64000, "input_cost_per_image_token": 0.0000021875, "input_cost_per_audio_token": 0.0000021875, "max_tokens": 64000, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "model_id": "apac.amazon.nova-2-pro-preview-20251202-v1:0", "model_name": "Nova 2 Pro Preview (Dec 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.1875, "output_cost_per_million": 17.5, "cache_read_cost_per_token": 5.46875e-7, "cache_read_cost_per_million": 0.546875, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000055, "max_input_tokens": 200000, "max_output_tokens": 64000, "supports_tool_search": true, "max_tokens": 64000, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-7, "output_cost_per_token_batches": 0.00000275, "model_id": "apac.anthropic.claude-haiku-4-5-20251001-v1:0", "model_name": "Claude Haiku 4 5 (Oct 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1.1, "output_cost_per_million": 5.5, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0.000001375, "cache_write_cost_per_million": 1.375, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "deprecation_date": "2026-10-14", "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, "model_id": "apac.anthropic.claude-sonnet-4-20250514-v1:0", "model_name": "Claude Sonnet 4 (May 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000055, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.0000022, "supports_tool_search": true, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-7, "output_cost_per_token_batches": 0.00000275, "model_id": "au.anthropic.claude-haiku-4-5-20251001-v1:0", "model_name": "Au.anthropic.claude Haiku 4 5 (Oct 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1.1, "output_cost_per_million": 5.5, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0.000001375, "cache_write_cost_per_million": 1.375, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000011, "supports_tool_search": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "model_id": "au.anthropic.claude-opus-4-6-v1", "model_name": "Au.anthropic.claude Opus 4 6 V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000011, "supports_tool_search": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, "model_id": "au.anthropic.claude-opus-4-7", "model_name": "Au.anthropic.claude Opus 4 7", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.000011, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "au.anthropic.claude-opus-4-8", "model_name": "Au.anthropic.claude Opus 4 8", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.000011, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "au.anthropic.claude-opus-5", "model_name": "Au.anthropic.claude Opus 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.0000066, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.0000132, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 0.00000165, "output_cost_per_token_batches": 0.00000825, "model_id": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", "model_name": "Au.anthropic.claude Sonnet 4 5 (Sep 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0.000004125, "cache_write_cost_per_million": 4.125, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 1000000, "max_output_tokens": 64000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.0000066, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "au.anthropic.claude-sonnet-4-6", "model_name": "Au.anthropic.claude Sonnet 4 6", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0.000004125, "cache_write_cost_per_million": 4.125, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.000011, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost_above_1hr": 0.0000044, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "au.anthropic.claude-sonnet-5", "model_name": "Au.anthropic.claude Sonnet 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.2, "output_cost_per_million": 11, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/google.gemma-4-26b-a4b", "model_name": "Google.gemma 4 26B A4B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.13, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/google.gemma-4-31b", "model_name": "Google.gemma 4 31B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.14, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "input_cost_per_token": 4e-8, "output_cost_per_token": 8e-8, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/google.gemma-4-e2b", "model_name": "Google.gemma 4 E2B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.04, "output_cost_per_million": 0.08, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.0000165, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 5.5e-7, "output_cost_per_token_above_272k_tokens": 0.00002475, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "model_id": "bedrock_mantle/openai.gpt-5.4", "model_name": "Openai.GPT-5.4", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 2.75e-7, "cache_read_cost_per_million": 0.275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.000011, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "output_cost_per_token_above_272k_tokens": 0.0000495, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "model_id": "bedrock_mantle/openai.gpt-5.5", "model_name": "Openai.GPT-5.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001375, "output_cost_per_token": 0.0000825, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "bedrock_mantle/openai.gpt-5.6-cyber", "model_name": "Openai.GPT-5.6 Cyber", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 13.75, "output_cost_per_million": 82.5, "cache_read_cost_per_token": 0.000001375, "cache_read_cost_per_million": 1.375, "cache_write_cost_per_token": 0.0000171875, "cache_write_cost_per_million": 17.1875, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 0.00000132, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 4.4e-7, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-7, "cache_read_input_token_cost_above_272k_tokens": 4.4e-8, "output_cost_per_token_above_272k_tokens": 0.00000198, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "model_id": "bedrock_mantle/openai.gpt-5.6-luna", "model_name": "Openai.GPT-5.6 Luna", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.22, "output_cost_per_million": 1.32, "cache_read_cost_per_token": 2.2e-8, "cache_read_cost_per_million": 0.022, "cache_write_cost_per_token": 2.75e-7, "cache_write_cost_per_million": 0.275, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.000011, "cache_creation_input_token_cost_above_272k_tokens": 0.00001375, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "output_cost_per_token_above_272k_tokens": 0.0000495, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "model_id": "bedrock_mantle/openai.gpt-5.6-sol", "model_name": "Openai.GPT-5.6 Sol", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.0000132, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.0000044, "cache_creation_input_token_cost_above_272k_tokens": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 4.4e-7, "output_cost_per_token_above_272k_tokens": 0.0000198, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "model_id": "bedrock_mantle/openai.gpt-5.6-terra", "model_name": "Openai.GPT-5.6 Terra", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.2, "output_cost_per_million": 13.200000000000001, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000011, "output_cost_per_token": 0.000055, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.000022, "cache_creation_input_token_cost_above_272k_tokens": 0.0000275, "cache_read_input_token_cost_above_272k_tokens": 0.0000022, "output_cost_per_token_above_272k_tokens": 0.0000825, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", "model_id": "bedrock_mantle/openai.gpt-6-astra", "model_name": "Openai.GPT-6 Astra", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 11, "output_cost_per_million": 55, "cache_read_cost_per_token": 0.0000011, "cache_read_cost_per_million": 1.1, "cache_write_cost_per_token": 0.00001375, "cache_write_cost_per_million": 13.75, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.000011, "cache_creation_input_token_cost_above_272k_tokens": 0.00001375, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "output_cost_per_token_above_272k_tokens": 0.0000495, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-daybreak-blue-56-sol.html", "model_id": "bedrock_mantle/openai.gpt-daybreak-blue-5.6-sol", "model_name": "Openai.GPT Daybreak Blue 5.6 Sol", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/openai.gpt-oss-120b", "model_name": "Openai.GPT Oss 120B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 7e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/openai.gpt-oss-20b", "model_name": "Openai.GPT Oss 20B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.07, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "supported_endpoints": [ "/v1/chat/completions" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/openai.gpt-oss-safeguard-120b", "model_name": "Openai.GPT Oss Safeguard 120B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 7e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "supported_endpoints": [ "/v1/chat/completions" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/openai.gpt-oss-safeguard-20b", "model_name": "Openai.GPT Oss Safeguard 20B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.07, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000198, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "bedrock_mantle/us-gov-east-1/openai.gpt-5.4", "model_name": "Openai.GPT-5.4", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 19.8, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 7.2e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/us-gov-east-1/openai.gpt-oss-120b", "model_name": "Openai.GPT Oss 120B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.18, "output_cost_per_million": 0.72, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 8.4e-8, "output_cost_per_token": 3.6e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/us-gov-east-1/openai.gpt-oss-20b", "model_name": "Openai.GPT Oss 20B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.08399999999999999, "output_cost_per_million": 0.36, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000264, "output_cost_per_token": 0.00000792, "max_input_tokens": 500000, "max_output_tokens": 500000, "use_openai_responses_path": true, "max_tokens": 500000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/us-gov-east-1/xai.grok-4.6", "model_name": "Xai.grok 4.6", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.64, "output_cost_per_million": 7.920000000000001, "cache_read_cost_per_token": 6.6e-7, "cache_read_cost_per_million": 0.66, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "input_cost_per_token": 1.56e-7, "output_cost_per_token": 4.8e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/us-gov-west-1/google.gemma-4-26b-a4b", "model_name": "Google.gemma 4 26B A4B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.156, "output_cost_per_million": 0.48, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "input_cost_per_token": 1.68e-7, "output_cost_per_token": 4.8e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/us-gov-west-1/google.gemma-4-31b", "model_name": "Google.gemma 4 31B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.16799999999999998, "output_cost_per_million": 0.48, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "input_cost_per_token": 4.8e-8, "output_cost_per_token": 9.6e-8, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/us-gov-west-1/google.gemma-4-e2b", "model_name": "Google.gemma 4 E2B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.048, "output_cost_per_million": 0.096, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000198, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "bedrock_mantle/us-gov-west-1/openai.gpt-5.4", "model_name": "Openai.GPT-5.4", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 19.8, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.64e-7, "output_cost_per_token": 0.000001584, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "input_cost_per_token_above_272k_tokens": 5.28e-7, "cache_creation_input_token_cost_above_272k_tokens": 6.6e-7, "cache_read_input_token_cost_above_272k_tokens": 5.28e-8, "output_cost_per_token_above_272k_tokens": 0.000002376, "model_id": "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna", "model_name": "Openai.GPT-5.6 Luna", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.26399999999999996, "output_cost_per_million": 1.584, "cache_read_cost_per_token": 2.64e-8, "cache_read_cost_per_million": 0.0264, "cache_write_cost_per_token": 3.3e-7, "cache_write_cost_per_million": 0.33, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000264, "output_cost_per_token": 0.00001584, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "input_cost_per_token_above_272k_tokens": 0.00000528, "cache_creation_input_token_cost_above_272k_tokens": 0.0000066, "cache_read_input_token_cost_above_272k_tokens": 5.28e-7, "output_cost_per_token_above_272k_tokens": 0.00002376, "model_id": "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra", "model_name": "Openai.GPT-5.6 Terra", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.64, "output_cost_per_million": 15.840000000000002, "cache_read_cost_per_token": 2.64e-7, "cache_read_cost_per_million": 0.26399999999999996, "cache_write_cost_per_token": 0.0000033, "cache_write_cost_per_million": 3.3000000000000003, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 7.2e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/us-gov-west-1/openai.gpt-oss-120b", "model_name": "Openai.GPT Oss 120B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.18, "output_cost_per_million": 0.72, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 8.4e-8, "output_cost_per_token": 3.6e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/us-gov-west-1/openai.gpt-oss-20b", "model_name": "Openai.GPT Oss 20B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.08399999999999999, "output_cost_per_million": 0.36, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000003, "max_input_tokens": 131072, "max_output_tokens": 16384, "use_openai_responses_path": true, "max_tokens": 16384, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "bedrock_mantle/us-gov-west-1/xai.grok-4.3", "model_name": "Xai.grok 4.3", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 2.4e-7, "cache_read_cost_per_million": 0.24, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000264, "output_cost_per_token": 0.00000792, "max_input_tokens": 500000, "max_output_tokens": 500000, "use_openai_responses_path": true, "max_tokens": 500000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/us-gov-west-1/xai.grok-4.6", "model_name": "Xai.grok 4.6", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.64, "output_cost_per_million": 7.920000000000001, "cache_read_cost_per_token": 6.6e-7, "cache_read_cost_per_million": 0.66, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 131072, "max_output_tokens": 16384, "use_openai_responses_path": true, "max_tokens": 16384, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "bedrock_mantle/xai.grok-4.3", "model_name": "Xai.grok 4.3", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.0000066, "max_input_tokens": 500000, "max_output_tokens": 500000, "use_openai_responses_path": true, "max_tokens": 500000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "bedrock_mantle/xai.grok-4.6", "model_name": "Xai.grok 4.6", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.2, "output_cost_per_million": 6.6000000000000005, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "supports_tool_search": true, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 0.0000015, "output_cost_per_token_batches": 0.0000075, "model_id": "claude-sonnet-4-5-20250929-v1:0", "model_name": "Claude Sonnet 4 5 (Sep 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5.8e-7, "output_cost_per_token": 0.00000168, "max_input_tokens": 163840, "max_output_tokens": 81920, "max_tokens": 81920, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "model_id": "deepseek.v3-v1:0", "model_name": "Deepseek.v3", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.58, "output_cost_per_million": 1.68, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6.2e-7, "output_cost_per_token": 0.00000185, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "deepseek.v3.2", "model_name": "Deepseek.v3.2", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.62, "output_cost_per_million": 1.85, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "eu-central-1/minimax.minimax-m2.5", "model_name": "Minimax.minimax M2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.36, "output_cost_per_million": 1.44, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.4e-7, "output_cost_per_token": 0.00000222, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "eu-north-1/deepseek.v3.2", "model_name": "Deepseek.v3.2", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.74, "output_cost_per_million": 2.2199999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "eu-north-1/minimax.minimax-m2.5", "model_name": "Minimax.minimax M2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.36, "output_cost_per_million": 1.44, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "eu-south-1/minimax.minimax-m2.5", "model_name": "Minimax.minimax M2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.36, "output_cost_per_million": 1.44, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "eu-west-1/minimax.minimax-m2.5", "model_name": "Minimax.minimax M2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.36, "output_cost_per_million": 1.44, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4.7e-7, "output_cost_per_token": 0.00000186, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "eu-west-2/minimax.minimax-m2.5", "model_name": "Minimax.minimax M2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.47, "output_cost_per_million": 1.8599999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3.3e-7, "output_cost_per_token": 0.00000275, "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "model_id": "eu.amazon.nova-2-lite-v1:0", "model_name": "Nova 2 Lite", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.33, "output_cost_per_million": 2.75, "cache_read_cost_per_token": 8.25e-8, "cache_read_cost_per_million": 0.0825, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000021875, "output_cost_per_token": 0.0000175, "max_input_tokens": 1000000, "max_output_tokens": 64000, "input_cost_per_image_token": 0.0000021875, "input_cost_per_audio_token": 0.0000021875, "max_tokens": 64000, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "model_id": "eu.amazon.nova-2-pro-preview-20251202-v1:0", "model_name": "Nova 2 Pro Preview (Dec 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.1875, "output_cost_per_million": 17.5, "cache_read_cost_per_token": 5.46875e-7, "cache_read_cost_per_million": 0.546875, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "eu.anthropic.claude-3-7-sonnet-20250219-v1:0", "model_name": "Claude 3 7 Sonnet (Feb 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000011, "output_cost_per_token": 0.000055, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000022, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "eu.anthropic.claude-fable-5", "model_name": "Claude Fable 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 11, "output_cost_per_million": 55, "cache_read_cost_per_token": 0.0000011, "cache_read_cost_per_million": 1.1, "cache_write_cost_per_token": 0.00001375, "cache_write_cost_per_million": 13.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000011, "output_cost_per_token": 0.000055, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000022, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "eu.anthropic.claude-fable-5-1", "model_name": "Claude Fable 5 1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 11, "output_cost_per_million": 55, "cache_read_cost_per_token": 2.75e-7, "cache_read_cost_per_million": 0.275, "cache_write_cost_per_token": 0.00001375, "cache_write_cost_per_million": 13.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000055, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-10-15", "cache_creation_input_token_cost_above_1hr": 0.0000022, "supports_tool_search": true, "max_tokens": 64000, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-7, "output_cost_per_token_batches": 0.00000275, "model_id": "eu.anthropic.claude-haiku-4-5-20251001-v1:0", "model_name": "Claude Haiku 4 5 (Oct 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1.1, "output_cost_per_million": 5.5, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0.000001375, "cache_write_cost_per_million": 1.375, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "deprecation_date": "2027-01-08", "max_tokens": 32000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "eu.anthropic.claude-opus-4-1-20250805-v1:0", "model_name": "Claude Opus 4 1 (Aug 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "eu.anthropic.claude-opus-4-20250514-v1:0", "model_name": "Claude Opus 4 (May 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "model_id": "eu.anthropic.claude-opus-4-5-20251101-v1:0", "model_name": "Claude Opus 4 5 (Nov 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000011, "supports_tool_search": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "model_id": "eu.anthropic.claude-opus-4-6-v1", "model_name": "Claude Opus 4 6 V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000011, "supports_tool_search": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, "model_id": "eu.anthropic.claude-opus-4-7", "model_name": "Claude Opus 4 7", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.000011, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "eu.anthropic.claude-opus-4-8", "model_name": "Claude Opus 4 8", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.000011, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "eu.anthropic.claude-opus-5", "model_name": "Claude Opus 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "deprecation_date": "2026-10-14", "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, "model_id": "eu.anthropic.claude-sonnet-4-20250514-v1:0", "model_name": "Claude Sonnet 4 (May 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.0000066, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.0000132, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 0.00000165, "output_cost_per_token_batches": 0.00000825, "model_id": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "model_name": "Claude Sonnet 4 5 (Sep 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0.000004125, "cache_write_cost_per_million": 4.125, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 1000000, "max_output_tokens": 64000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.0000066, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "eu.anthropic.claude-sonnet-4-6", "model_name": "Claude Sonnet 4 6", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0.000004125, "cache_write_cost_per_million": 4.125, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.000011, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost_above_1hr": 0.0000044, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "eu.anthropic.claude-sonnet-5", "model_name": "Claude Sonnet 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.2, "output_cost_per_million": 11, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.4e-7, "output_cost_per_token": 0.00000222, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "model_id": "eu.deepseek.v3.2", "model_name": "V3.2", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.74, "output_cost_per_million": 2.2199999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "model_id": "global.amazon.nova-2-lite-v1:0", "model_name": "Global.amazon.nova 2 Lite", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.00002, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "global.anthropic.claude-fable-5", "model_name": "Global.anthropic.claude Fable 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.00002, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "global.anthropic.claude-fable-5-1", "model_name": "Global.anthropic.claude Fable 5 1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000002, "supports_tool_search": true, "max_tokens": 64000, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5e-7, "output_cost_per_token_batches": 0.0000025, "model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0", "model_name": "Global.anthropic.claude Haiku 4 5 (Oct 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.00001, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0", "model_name": "Global.anthropic.claude Opus 4 5 (Nov 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "supports_tool_search": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "model_id": "global.anthropic.claude-opus-4-6-v1", "model_name": "Global.anthropic.claude Opus 4 6 V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "supports_tool_search": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, "model_id": "global.anthropic.claude-opus-4-7", "model_name": "Global.anthropic.claude Opus 4 7", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "global.anthropic.claude-opus-4-8", "model_name": "Global.anthropic.claude Opus 4 8", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "global.anthropic.claude-opus-5", "model_name": "Global.anthropic.claude Opus 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "deprecation_date": "2026-10-14", "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, "model_id": "global.anthropic.claude-sonnet-4-20250514-v1:0", "model_name": "Global.anthropic.claude Sonnet 4 (May 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 0.0000015, "output_cost_per_token_batches": 0.0000075, "model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", "model_name": "Global.anthropic.claude Sonnet 4 5 (Sep 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000006, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "global.anthropic.claude-sonnet-4-6", "model_name": "Global.anthropic.claude Sonnet 4 6", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost_above_1hr": 0.000004, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "global.anthropic.claude-sonnet-5", "model_name": "Global.anthropic.claude Sonnet 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 4e-7, "cache_creation_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "output_cost_per_token_above_272k_tokens": 0.0000018, "max_tokens": 128000, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "model_id": "global.openai.gpt-5.6-luna", "model_name": "Global.openai.GPT-5.6 Luna", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 2.5e-7, "cache_write_cost_per_million": 0.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.000008, "cache_creation_input_token_cost_above_272k_tokens": 0.00001, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "output_cost_per_token_above_272k_tokens": 0.00003, "max_tokens": 128000, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "model_id": "global.openai.gpt-5.6-sol", "model_name": "Global.openai.GPT-5.6 Sol", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.000004, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "output_cost_per_token_above_272k_tokens": 0.000018, "max_tokens": 128000, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "model_id": "global.openai.gpt-5.6-terra", "model_name": "Global.openai.GPT-5.6 Terra", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00002, "cache_creation_input_token_cost_above_272k_tokens": 0.000025, "cache_read_input_token_cost_above_272k_tokens": 0.000002, "output_cost_per_token_above_272k_tokens": 0.000075, "max_tokens": 128000, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", "model_id": "global.openai.gpt-6-astra", "model_name": "Global.openai.GPT-6 Astra", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 500000, "max_tokens": 500000, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "global.xai.grok-4.6", "model_name": "Global.xai.grok 4.6", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000055, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.0000022, "supports_tool_search": true, "max_tokens": 64000, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-7, "output_cost_per_token_batches": 0.00000275, "model_id": "jp.anthropic.claude-haiku-4-5-20251001-v1:0", "model_name": "Jp.anthropic.claude Haiku 4 5 (Oct 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1.1, "output_cost_per_million": 5.5, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0.000001375, "cache_write_cost_per_million": 1.375, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_tool_search": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, "model_id": "jp.anthropic.claude-opus-4-7", "model_name": "Jp.anthropic.claude Opus 4 7", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.000011, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "jp.anthropic.claude-opus-4-8", "model_name": "Jp.anthropic.claude Opus 4 8", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.000011, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "jp.anthropic.claude-opus-5", "model_name": "Jp.anthropic.claude Opus 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.0000066, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.0000132, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 0.00000165, "output_cost_per_token_batches": 0.00000825, "model_id": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "model_name": "Jp.anthropic.claude Sonnet 4 5 (Sep 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0.000004125, "cache_write_cost_per_million": 4.125, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 1000000, "max_output_tokens": 64000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.0000066, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "jp.anthropic.claude-sonnet-4-6", "model_name": "Jp.anthropic.claude Sonnet 4 6", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0.000004125, "cache_write_cost_per_million": 4.125, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.000011, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost_above_1hr": 0.0000044, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "jp.anthropic.claude-sonnet-5", "model_name": "Jp.anthropic.claude Sonnet 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.2, "output_cost_per_million": 11, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_reasoning": true, "supports_system_messages": true, "model_id": "mistral.magistral-small-2509", "model_name": "Magistral Small (Sep 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.5, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_reasoning": true, "supports_system_messages": true, "supports_native_structured_output": true, "model_id": "moonshot.kimi-k2-thinking", "model_name": "Moonshot.kimi K2 Thinking", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.6, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.3e-7, "output_cost_per_token": 0.00000303, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "model_id": "moonshotai.kimi-k2-thinking", "model_name": "Moonshotai.kimi K2 Thinking", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.73, "output_cost_per_million": 3.03, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6.5e-7, "max_input_tokens": 256000, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "nvidia.nemotron-super-3-120b", "model_name": "Nvidia.nemotron Super 3 120B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.15, "output_cost_per_million": 0.65, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openai.gpt-oss-120b-1:0", "model_name": "Openai.GPT Oss 120B 1:0", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 7e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openai.gpt-oss-20b-1:0", "model_name": "Openai.GPT Oss 20B 1:0", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.07, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7, "max_input_tokens": 262144, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "input_cost_per_token_batches": 1.1e-7, "output_cost_per_token_batches": 4.4e-7, "model_id": "qwen.qwen3-235b-a22b-2507-v1:0", "model_name": "Qwen.qwen3 235B A22B (Jul 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.22, "output_cost_per_million": 0.88, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "model_id": "qwen.qwen3-32b-v1:0", "model_name": "Qwen.qwen3 32B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 262144, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "model_id": "qwen.qwen3-coder-30b-a3b-v1:0", "model_name": "Qwen.qwen3 Coder 30B A3B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4.5e-7, "output_cost_per_token": 0.0000018, "max_input_tokens": 262000, "max_output_tokens": 65536, "max_tokens": 65536, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-west-2/index.json", "model_id": "qwen.qwen3-coder-480b-a35b-v1:0", "model_name": "Qwen.qwen3 Coder 480B A35B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.44999999999999996, "output_cost_per_million": 1.7999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.4e-7, "output_cost_per_token": 0.00000222, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "sa-east-1/deepseek.v3.2", "model_name": "Deepseek.v3.2", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.74, "output_cost_per_million": 2.2199999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "sa-east-1/minimax.minimax-m2.5", "model_name": "Minimax.minimax M2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.36, "output_cost_per_million": 1.44, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.3e-7, "output_cost_per_token": 0.00000303, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "model_id": "sa-east-1/moonshotai.kimi-k2-thinking", "model_name": "Moonshotai.kimi K2 Thinking", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.73, "output_cost_per_million": 3.03, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6.2e-7, "output_cost_per_token": 0.00000185, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-east-1/deepseek.v3.2", "model_name": "Deepseek.v3.2", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.62, "output_cost_per_million": 1.85, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "model_id": "us-east-1/moonshotai.kimi-k2-thinking", "model_name": "Moonshotai.kimi K2 Thinking", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.6, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032, "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "supports_system_messages": true, "supports_native_structured_output": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-east-1/zai.glm-5", "model_name": "Zai.glm 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1, "output_cost_per_million": 3.1999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6.2e-7, "output_cost_per_token": 0.00000185, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-east-2/deepseek.v3.2", "model_name": "Deepseek.v3.2", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.62, "output_cost_per_million": 1.85, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "us-east-2/minimax.minimax-m2.5", "model_name": "Minimax.minimax M2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "model_id": "us-east-2/moonshotai.kimi-k2-thinking", "model_name": "Moonshotai.kimi K2 Thinking", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.6, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000012, "output_cost_per_token": 0.00006, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000024, "max_tokens": 128000, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "us-gov-east-1/anthropic.claude-fable-5-1", "model_name": "Anthropic.claude Fable 5 1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 12, "output_cost_per_million": 60, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.000015, "cache_write_cost_per_million": 15, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.0000024, "supports_tool_search": true, "max_tokens": 64000, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "model_id": "us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0", "model_name": "Anthropic.claude Haiku 4 5 (Oct 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1.2, "output_cost_per_million": 6, "cache_read_cost_per_token": 1.2e-7, "cache_read_cost_per_million": 0.12, "cache_write_cost_per_token": 0.0000015, "cache_write_cost_per_million": 1.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000006, "output_cost_per_token": 0.00003, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost_above_1hr": 0.000012, "max_tokens": 128000, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "us-gov-east-1/anthropic.claude-opus-4-8", "model_name": "Anthropic.claude Opus 4 8", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 6, "output_cost_per_million": 30, "cache_read_cost_per_token": 6e-7, "cache_read_cost_per_million": 0.6, "cache_write_cost_per_token": 0.0000075, "cache_write_cost_per_million": 7.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000006, "output_cost_per_token": 0.00003, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost_above_1hr": 0.000012, "max_tokens": 128000, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "us-gov-east-1/anthropic.claude-opus-5", "model_name": "Anthropic.claude Opus 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 6, "output_cost_per_million": 30, "cache_read_cost_per_token": 6e-7, "cache_read_cost_per_million": 0.6, "cache_write_cost_per_token": 0.0000075, "cache_write_cost_per_million": 7.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000036, "output_cost_per_token": 0.000018, "max_input_tokens": 200000, "max_output_tokens": 8192, "cache_creation_input_token_cost_above_1hr": 0.0000072, "supports_tool_search": true, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0", "model_name": "Anthropic.claude Sonnet 4 5 (Sep 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.5999999999999996, "output_cost_per_million": 18, "cache_read_cost_per_token": 3.6e-7, "cache_read_cost_per_million": 0.36, "cache_write_cost_per_token": 0.0000045, "cache_write_cost_per_million": 4.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost_above_1hr": 0.0000048, "max_tokens": 128000, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "us-gov-east-1/anthropic.claude-sonnet-5", "model_name": "Anthropic.claude Sonnet 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.4, "output_cost_per_million": 12, "cache_read_cost_per_token": 2.4e-7, "cache_read_cost_per_million": 0.24, "cache_write_cost_per_token": 0.000003, "cache_write_cost_per_million": 3, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000036, "output_cost_per_token": 0.000018, "max_input_tokens": 200000, "max_output_tokens": 8192, "cache_creation_input_token_cost_above_1hr": 0.0000072, "supports_tool_search": true, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "us-gov-east-1/claude-sonnet-4-5-20250929-v1:0", "model_name": "Claude Sonnet 4 5 (Sep 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.5999999999999996, "output_cost_per_million": 18, "cache_read_cost_per_token": 3.6e-7, "cache_read_cost_per_million": 0.36, "cache_write_cost_per_token": 0.0000045, "cache_write_cost_per_million": 4.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 7.8e-7, "max_input_tokens": 256000, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "us-gov-east-1/nvidia.nemotron-super-3-120b", "model_name": "Nvidia.nemotron Super 3 120B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.18, "output_cost_per_million": 0.78, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 7.2e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "us-gov-east-1/openai.gpt-oss-120b-1:0", "model_name": "Openai.GPT Oss 120B 1:0", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.18, "output_cost_per_million": 0.72, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 8.4e-8, "output_cost_per_token": 3.6e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "us-gov-east-1/openai.gpt-oss-20b-1:0", "model_name": "Openai.GPT Oss 20B 1:0", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.08399999999999999, "output_cost_per_million": 0.36, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000036, "output_cost_per_token": 0.000018, "max_input_tokens": 200000, "max_output_tokens": 8192, "deprecation_date": "2026-07-30", "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0", "model_name": "Anthropic.claude 3 7 Sonnet (Feb 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.5999999999999996, "output_cost_per_million": 18, "cache_read_cost_per_token": 3.6e-7, "cache_read_cost_per_million": 0.36, "cache_write_cost_per_token": 0.0000045, "cache_write_cost_per_million": 4.5, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000012, "output_cost_per_token": 0.00006, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000024, "max_tokens": 128000, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "us-gov-west-1/anthropic.claude-fable-5-1", "model_name": "Anthropic.claude Fable 5 1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 12, "output_cost_per_million": 60, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.000015, "cache_write_cost_per_million": 15, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.0000024, "supports_tool_search": true, "max_tokens": 64000, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "model_id": "us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0", "model_name": "Anthropic.claude Haiku 4 5 (Oct 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1.2, "output_cost_per_million": 6, "cache_read_cost_per_token": 1.2e-7, "cache_read_cost_per_million": 0.12, "cache_write_cost_per_token": 0.0000015, "cache_write_cost_per_million": 1.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000006, "output_cost_per_token": 0.00003, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost_above_1hr": 0.000012, "max_tokens": 128000, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "us-gov-west-1/anthropic.claude-opus-4-8", "model_name": "Anthropic.claude Opus 4 8", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 6, "output_cost_per_million": 30, "cache_read_cost_per_token": 6e-7, "cache_read_cost_per_million": 0.6, "cache_write_cost_per_token": 0.0000075, "cache_write_cost_per_million": 7.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000006, "output_cost_per_token": 0.00003, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost_above_1hr": 0.000012, "max_tokens": 128000, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "us-gov-west-1/anthropic.claude-opus-5", "model_name": "Anthropic.claude Opus 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 6, "output_cost_per_million": 30, "cache_read_cost_per_token": 6e-7, "cache_read_cost_per_million": 0.6, "cache_write_cost_per_token": 0.0000075, "cache_write_cost_per_million": 7.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000036, "output_cost_per_token": 0.000018, "max_input_tokens": 200000, "max_output_tokens": 8192, "cache_creation_input_token_cost_above_1hr": 0.0000072, "supports_tool_search": true, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0", "model_name": "Anthropic.claude Sonnet 4 5 (Sep 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.5999999999999996, "output_cost_per_million": 18, "cache_read_cost_per_token": 3.6e-7, "cache_read_cost_per_million": 0.36, "cache_write_cost_per_token": 0.0000045, "cache_write_cost_per_million": 4.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost_above_1hr": 0.0000048, "max_tokens": 128000, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "us-gov-west-1/anthropic.claude-sonnet-5", "model_name": "Anthropic.claude Sonnet 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.4, "output_cost_per_million": 12, "cache_read_cost_per_token": 2.4e-7, "cache_read_cost_per_million": 0.24, "cache_write_cost_per_token": 0.000003, "cache_write_cost_per_million": 3, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000036, "output_cost_per_token": 0.000018, "max_input_tokens": 200000, "max_output_tokens": 8192, "cache_creation_input_token_cost_above_1hr": 0.0000072, "supports_tool_search": true, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "us-gov-west-1/claude-sonnet-4-5-20250929-v1:0", "model_name": "Claude Sonnet 4 5 (Sep 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.5999999999999996, "output_cost_per_million": 18, "cache_read_cost_per_token": 3.6e-7, "cache_read_cost_per_million": 0.36, "cache_write_cost_per_token": 0.0000045, "cache_write_cost_per_million": 4.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 7.8e-7, "max_input_tokens": 256000, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "us-gov-west-1/nvidia.nemotron-super-3-120b", "model_name": "Nvidia.nemotron Super 3 120B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.18, "output_cost_per_million": 0.78, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 7.2e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "us-gov-west-1/openai.gpt-oss-120b-1:0", "model_name": "Openai.GPT Oss 120B 1:0", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.18, "output_cost_per_million": 0.72, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 8.4e-8, "output_cost_per_token": 3.6e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "us-gov-west-1/openai.gpt-oss-20b-1:0", "model_name": "Openai.GPT Oss 20B 1:0", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.08399999999999999, "output_cost_per_million": 0.36, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000012, "output_cost_per_token": 0.00006, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000024, "max_tokens": 128000, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "us-gov.anthropic.claude-fable-5-1", "model_name": "Us Gov.anthropic.claude Fable 5 1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 12, "output_cost_per_million": 60, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.000015, "cache_write_cost_per_million": 15, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000006, "output_cost_per_token": 0.00003, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost_above_1hr": 0.000012, "max_tokens": 128000, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "us-gov.anthropic.claude-opus-4-8", "model_name": "Us Gov.anthropic.claude Opus 4 8", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 6, "output_cost_per_million": 30, "cache_read_cost_per_token": 6e-7, "cache_read_cost_per_million": 0.6, "cache_write_cost_per_token": 0.0000075, "cache_write_cost_per_million": 7.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000006, "output_cost_per_token": 0.00003, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost_above_1hr": 0.000012, "max_tokens": 128000, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "us-gov.anthropic.claude-opus-5", "model_name": "Us Gov.anthropic.claude Opus 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 6, "output_cost_per_million": 30, "cache_read_cost_per_token": 6e-7, "cache_read_cost_per_million": 0.6, "cache_write_cost_per_token": 0.0000075, "cache_write_cost_per_million": 7.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000036, "output_cost_per_token": 0.000018, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.0000072, "input_cost_per_token_above_200k_tokens": 0.0000072, "output_cost_per_token_above_200k_tokens": 0.000027, "cache_creation_input_token_cost_above_200k_tokens": 0.000009, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.0000144, "cache_read_input_token_cost_above_200k_tokens": 7.2e-7, "supports_tool_search": true, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0", "model_name": "Us Gov.anthropic.claude Sonnet 4 5 (Sep 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.5999999999999996, "output_cost_per_million": 18, "cache_read_cost_per_token": 3.6e-7, "cache_read_cost_per_million": 0.36, "cache_write_cost_per_token": 0.0000045, "cache_write_cost_per_million": 4.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost_above_1hr": 0.0000048, "max_tokens": 128000, "prompt_cache_min_tokens": 1024, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_mid_conversation_system": true, "supports_native_structured_output": false, "supports_output_config": true, "supports_parallel_tool_use_config": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "us-gov.anthropic.claude-sonnet-5", "model_name": "Us Gov.anthropic.claude Sonnet 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.4, "output_cost_per_million": 12, "cache_read_cost_per_token": 2.4e-7, "cache_read_cost_per_million": 0.24, "cache_write_cost_per_token": 0.000003, "cache_write_cost_per_million": 3, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 7.8e-7, "max_input_tokens": 256000, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "us-gov.nvidia.nemotron-super-3-120b", "model_name": "Us Gov.nvidia.nemotron Super 3 120B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.18, "output_cost_per_million": 0.78, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 7.2e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "us-gov.openai.gpt-oss-120b-1:0", "model_name": "Us Gov.openai.GPT Oss 120B 1:0", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.18, "output_cost_per_million": 0.72, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 8.4e-8, "output_cost_per_token": 3.6e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "us-gov.openai.gpt-oss-20b-1:0", "model_name": "Us Gov.openai.GPT Oss 20B 1:0", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.08399999999999999, "output_cost_per_million": 0.36, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000264, "output_cost_per_token": 0.00000792, "max_input_tokens": 500000, "max_output_tokens": 500000, "max_tokens": 500000, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "us-gov.xai.grok-4.6", "model_name": "Us Gov.xai.grok 4.6", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.64, "output_cost_per_million": 7.920000000000001, "cache_read_cost_per_token": 6.6e-7, "cache_read_cost_per_million": 0.66, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6.2e-7, "output_cost_per_token": 0.00000185, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-west-2/deepseek.v3.2", "model_name": "Deepseek.v3.2", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.62, "output_cost_per_million": 1.85, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "model_id": "us-west-2/moonshotai.kimi-k2-thinking", "model_name": "Moonshotai.kimi K2 Thinking", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.6, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032, "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "supports_system_messages": true, "supports_native_structured_output": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-west-2/zai.glm-5", "model_name": "Zai.glm 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1, "output_cost_per_million": 3.1999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3.3e-7, "output_cost_per_token": 0.00000275, "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "model_id": "us.amazon.nova-2-lite-v1:0", "model_name": "Nova 2 Lite", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.33, "output_cost_per_million": 2.75, "cache_read_cost_per_token": 8.25e-8, "cache_read_cost_per_million": 0.0825, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000021875, "output_cost_per_token": 0.0000175, "max_input_tokens": 1000000, "max_output_tokens": 64000, "input_cost_per_image_token": 0.0000021875, "input_cost_per_audio_token": 0.0000021875, "max_tokens": 64000, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "model_id": "us.amazon.nova-2-pro-preview-20251202-v1:0", "model_name": "Nova 2 Pro Preview (Dec 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.1875, "output_cost_per_million": 17.5, "cache_read_cost_per_token": 5.46875e-7, "cache_read_cost_per_million": 0.546875, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "us.anthropic.claude-3-7-sonnet-20250219-v1:0", "model_name": "Claude 3 7 Sonnet (Feb 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000011, "output_cost_per_token": 0.000055, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000022, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "us.anthropic.claude-fable-5", "model_name": "Claude Fable 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 11, "output_cost_per_million": 55, "cache_read_cost_per_token": 0.0000011, "cache_read_cost_per_million": 1.1, "cache_write_cost_per_token": 0.00001375, "cache_write_cost_per_million": 13.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000011, "output_cost_per_token": 0.000055, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000022, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "us.anthropic.claude-fable-5-1", "model_name": "Claude Fable 5 1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 11, "output_cost_per_million": 55, "cache_read_cost_per_token": 2.75e-7, "cache_read_cost_per_million": 0.275, "cache_write_cost_per_token": 0.00001375, "cache_write_cost_per_million": 13.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000055, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.0000022, "supports_tool_search": true, "max_tokens": 64000, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "input_cost_per_token_batches": 5.5e-7, "output_cost_per_token_batches": 0.00000275, "model_id": "us.anthropic.claude-haiku-4-5-20251001-v1:0", "model_name": "Claude Haiku 4 5 (Oct 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1.1, "output_cost_per_million": 5.5, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0.000001375, "cache_write_cost_per_million": 1.375, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "deprecation_date": "2027-01-08", "max_tokens": 32000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "us.anthropic.claude-opus-4-1-20250805-v1:0", "model_name": "Claude Opus 4 1 (Aug 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "us.anthropic.claude-opus-4-20250514-v1:0", "model_name": "Claude Opus 4 (May 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000011, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "high", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "model_id": "us.anthropic.claude-opus-4-5-20251101-v1:0", "model_name": "Claude Opus 4 5 (Nov 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000011, "supports_tool_search": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "bedrock_output_config_effort_ceiling": "max", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 4096, "model_id": "us.anthropic.claude-opus-4-6-v1", "model_name": "Claude Opus 4 6 V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000011, "supports_tool_search": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 2048, "model_id": "us.anthropic.claude-opus-4-7", "model_name": "Claude Opus 4 7", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.000011, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "us.anthropic.claude-opus-4-8", "model_name": "Claude Opus 4 8", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.0000275, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.000011, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 512, "model_id": "us.anthropic.claude-opus-5", "model_name": "Claude Opus 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 27.5, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0.000006875, "cache_write_cost_per_million": 6.875, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "deprecation_date": "2026-10-14", "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "bedrock_converse_supports_strict_tools": false, "prompt_cache_min_tokens": 1024, "model_id": "us.anthropic.claude-sonnet-4-20250514-v1:0", "model_name": "Claude Sonnet 4 (May 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.0000066, "input_cost_per_token_above_200k_tokens": 0.0000066, "output_cost_per_token_above_200k_tokens": 0.00002475, "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.0000132, "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "input_cost_per_token_batches": 0.00000165, "output_cost_per_token_batches": 0.00000825, "model_id": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "model_name": "Claude Sonnet 4 5 (Sep 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0.000004125, "cache_write_cost_per_million": 4.125, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 1000000, "max_output_tokens": 64000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.0000066, "supports_tool_search": true, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_native_structured_output": true, "supports_output_config": true, "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "us.anthropic.claude-sonnet-4-6", "model_name": "Claude Sonnet 4 6", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0.000004125, "cache_write_cost_per_million": 4.125, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.000011, "max_input_tokens": 1000000, "max_output_tokens": 128000, "bedrock_converse_supports_strict_tools": false, "cache_creation_input_token_cost_above_1hr": 0.0000044, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_mid_conversation_system": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_native_structured_output": false, "supports_max_reasoning_effort": true, "supports_output_config": true, "bedrock_output_config_effort_ceiling": "xhigh", "supports_parallel_tool_use_config": true, "prompt_cache_min_tokens": 1024, "model_id": "us.anthropic.claude-sonnet-5", "model_name": "Claude Sonnet 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.2, "output_cost_per_million": 11, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_reasoning": true, "supports_tool_choice": false, "model_id": "us.deepseek.r1-v1:0", "model_name": "R1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1.35, "output_cost_per_million": 5.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6.2e-7, "output_cost_per_token": 0.00000185, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "model_id": "us.deepseek.v3.2", "model_name": "V3.2", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.62, "output_cost_per_million": 1.85, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 0.00000132, "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 4.4e-7, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-7, "cache_read_input_token_cost_above_272k_tokens": 4.4e-8, "output_cost_per_token_above_272k_tokens": 0.00000198, "max_tokens": 128000, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "model_id": "us.openai.gpt-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.22, "output_cost_per_million": 1.32, "cache_read_cost_per_token": 2.2e-8, "cache_read_cost_per_million": 0.022, "cache_write_cost_per_token": 2.75e-7, "cache_write_cost_per_million": 0.275, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.0000044, "output_cost_per_token": 0.000022, "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.0000088, "cache_creation_input_token_cost_above_272k_tokens": 0.000011, "cache_read_input_token_cost_above_272k_tokens": 8.8e-7, "output_cost_per_token_above_272k_tokens": 0.000033, "max_tokens": 128000, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "model_id": "us.openai.gpt-5.6-sol", "model_name": "GPT-5.6 Sol", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 4.4, "output_cost_per_million": 22, "cache_read_cost_per_token": 4.4e-7, "cache_read_cost_per_million": 0.44, "cache_write_cost_per_token": 0.0000055, "cache_write_cost_per_million": 5.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.0000132, "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.0000044, "cache_creation_input_token_cost_above_272k_tokens": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 4.4e-7, "output_cost_per_token_above_272k_tokens": 0.0000198, "max_tokens": 128000, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "model_id": "us.openai.gpt-5.6-terra", "model_name": "GPT-5.6 Terra", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.2, "output_cost_per_million": 13.200000000000001, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000011, "output_cost_per_token": 0.000055, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.000022, "cache_creation_input_token_cost_above_272k_tokens": 0.0000275, "cache_read_input_token_cost_above_272k_tokens": 0.0000022, "output_cost_per_token_above_272k_tokens": 0.0000825, "max_tokens": 128000, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", "model_id": "us.openai.gpt-6-astra", "model_name": "GPT-6 Astra", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 11, "output_cost_per_million": 55, "cache_read_cost_per_token": 0.0000011, "cache_read_cost_per_million": 1.1, "cache_write_cost_per_token": 0.00001375, "cache_write_cost_per_million": 13.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.0000066, "max_input_tokens": 500000, "max_output_tokens": 500000, "max_tokens": 500000, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "us.xai.grok-4.6", "model_name": "Grok 4.6", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.2, "output_cost_per_million": 6.6000000000000005, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "zai.glm-4.7", "model_name": "Zai.glm 4.7", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.6, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "zai.glm-4.7-flash", "model_name": "Zai.glm 4.7 Flash", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.07, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032, "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "zai.glm-5", "model_name": "Zai.glm 5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1, "output_cost_per_million": 3.1999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.9e-7, "output_cost_per_token": 0.00000149, "max_input_tokens": 131072, "max_output_tokens": 40960, "max_tokens": 40960, "source": "https://api.cerebras.ai/public/v1/models/gemma-4-31b", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "cerebras/gemma-4-31b", "model_name": "Gemma 4 31B", "provider_id": "cerebras", "provider_name": "Cerebras", "input_cost_per_million": 0.9900000000000001, "output_cost_per_million": 1.49, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 7.5e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "cerebras/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "cerebras", "provider_name": "Cerebras", "input_cost_per_million": 0.35, "output_cost_per_million": 0.75, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://inference-docs.cerebras.ai/support/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "cerebras/qwen-3-32b", "model_name": "Qwen 3 32B", "provider_id": "cerebras", "provider_name": "Cerebras", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 0.7999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.9e-7, "output_cost_per_token": 0.00000149, "max_input_tokens": 65536, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://api.cerebras.ai/public/v1/models/qwen-3.8-27b", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "cerebras/qwen-3.8-27b", "model_name": "Qwen 3.8 27B", "provider_id": "cerebras", "provider_name": "Cerebras", "input_cost_per_million": 0.9900000000000001, "output_cost_per_million": 1.49, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "input_cost_per_token": 0.00000225, "output_cost_per_token": 0.00000275, "max_input_tokens": 128000, "max_output_tokens": 128000, "deprecation_date": "2026-01-20", "max_tokens": 128000, "source": "https://www.cerebras.ai/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "cerebras/zai-glm-4.6", "model_name": "Zai Glm 4.6", "provider_id": "cerebras", "provider_name": "Cerebras", "input_cost_per_million": 2.25, "output_cost_per_million": 2.75, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000225, "output_cost_per_token": 0.00000275, "max_input_tokens": 128000, "max_output_tokens": 128000, "deprecation_date": "2026-08-17", "max_tokens": 128000, "source": "https://www.cerebras.ai/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "cerebras/zai-glm-4.7", "model_name": "Zai Glm 4.7", "provider_id": "cerebras", "provider_name": "Cerebras", "input_cost_per_million": 2.25, "output_cost_per_million": 2.75, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 4.97e-7, "output_cost_per_token": 0.000004881, "max_input_tokens": 80000, "max_output_tokens": 80000, "max_tokens": 80000, "rpm": 300, "supports_reasoning": true, "model_id": "@cf/deepseek-ai/deepseek-r1-distill-qwen-32b", "model_name": "Deepseek R1 Distill Qwen 32B", "provider_id": "cloudflare", "provider_name": "Cloudflare", "input_cost_per_million": 0.49699999999999994, "output_cost_per_million": 4.881, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "rpm": 300, "supports_reasoning": true, "model_id": "@cf/google/gemma-4-26b-a4b-it", "model_name": "Gemma 4 26B A4B It", "provider_id": "cloudflare", "provider_name": "Cloudflare", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "rpm": 20, "supports_reasoning": true, "model_id": "@cf/moonshotai/kimi-k2.6", "model_name": "Kimi K2.6", "provider_id": "cloudflare", "provider_name": "Cloudflare", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.6e-7, "cache_read_cost_per_million": 0.16, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "rpm": 20, "supports_reasoning": true, "model_id": "@cf/moonshotai/kimi-k2.7-code", "model_name": "Kimi K2.7 Code", "provider_id": "cloudflare", "provider_name": "Cloudflare", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.9e-7, "cache_read_cost_per_million": 0.19, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "rpm": 300, "supports_reasoning": true, "model_id": "@cf/nvidia/nemotron-3-120b-a12b", "model_name": "Nemotron 3 120B A12B", "provider_id": "cloudflare", "provider_name": "Cloudflare", "input_cost_per_million": 0.5, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 7.5e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "rpm": 300, "supports_reasoning": true, "model_id": "@cf/openai/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "cloudflare", "provider_name": "Cloudflare", "input_cost_per_million": 0.35, "output_cost_per_million": 0.75, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "rpm": 300, "supports_reasoning": true, "model_id": "@cf/openai/gpt-oss-20b", "model_name": "GPT Oss 20B", "provider_id": "cloudflare", "provider_name": "Cloudflare", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5.09e-8, "output_cost_per_token": 3.35e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "rpm": 300, "supports_reasoning": true, "model_id": "@cf/qwen/qwen3-30b-a3b-fp8", "model_name": "Qwen3 30B A3B Fp8", "provider_id": "cloudflare", "provider_name": "Cloudflare", "input_cost_per_million": 0.0509, "output_cost_per_million": 0.335, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6.6e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 24000, "max_output_tokens": 24000, "max_tokens": 24000, "rpm": 300, "supports_reasoning": true, "model_id": "@cf/qwen/qwq-32b", "model_name": "Qwen QwQ 32B", "provider_id": "cloudflare", "provider_name": "Cloudflare", "input_cost_per_million": 0.66, "output_cost_per_million": 1, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6.05e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "rpm": 300, "supports_reasoning": true, "model_id": "@cf/zai-org/glm-4.7-flash", "model_name": "Glm 4.7 Flash", "provider_id": "cloudflare", "provider_name": "Cloudflare", "input_cost_per_million": 0.060500000000000005, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "rpm": 20, "supports_reasoning": true, "model_id": "@cf/zai-org/glm-5.2", "model_name": "Glm 5.2", "provider_id": "cloudflare", "provider_name": "Cloudflare", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000007, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "model_id": "crusoe/deepseek-ai/DeepSeek-R1-0528", "model_name": "DeepSeek R1 0528", "provider_id": "crusoe", "provider_name": "Crusoe", "input_cost_per_million": 3, "output_cost_per_million": 7, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.0000025, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "model_id": "crusoe/moonshotai/Kimi-K2-Thinking", "model_name": "Kimi K2 Thinking", "provider_id": "crusoe", "provider_name": "Crusoe", "input_cost_per_million": 2.5, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/deepseek-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 4e-8, "cache_read_cost_per_million": 0.04, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/deepseek-v4-flash-0731", "model_name": "Deepseek V4 Flash 0731", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 4e-8, "cache_read_cost_per_million": 0.04, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.0000048, "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/deepseek-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 2.4, "output_cost_per_million": 4.8, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 202745, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/glm-5.1", "model_name": "Glm 5.1", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/glm-5.2", "model_name": "Glm 5.2", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 229376, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/kimi-k2.7-code", "model_name": "Kimi K2.7 Code", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.9e-7, "cache_read_cost_per_million": 0.19, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen-coder", "model_name": "Qwen Coder", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.3, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "range": [ 0, 256000 ] }, { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "range": [ 256000, 1000000 ] } ], "model_id": "dashscope/qwen-flash", "model_name": "Qwen Flash", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "range": [ 0, 256000 ] }, { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "range": [ 256000, 1000000 ] } ], "model_id": "dashscope/qwen-flash-2025-07-28", "model_name": "Qwen Flash (Jul 2025)", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000016, "output_cost_per_token": 0.0000064, "max_input_tokens": 30720, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen-max", "model_name": "Qwen Max", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 1.5999999999999999, "output_cost_per_million": 6.3999999999999995, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen-plus", "model_name": "Qwen Plus", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 129024, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen-plus-2025-01-25", "model_name": "Qwen Plus (Jan 2025)", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 0.000004, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen-plus-2025-04-28", "model_name": "Qwen Plus (Apr 2025)", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 0.000004, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen-plus-2025-07-14", "model_name": "Qwen Plus (Jul 2025)", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012, "range": [ 0, 256000 ] }, { "input_cost_per_token": 0.0000012, "output_cost_per_reasoning_token": 0.000012, "output_cost_per_token": 0.0000036, "range": [ 256000, 1000000 ] } ], "model_id": "dashscope/qwen-plus-2025-07-28", "model_name": "Qwen Plus (Jul 2025)", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012, "range": [ 0, 256000 ] }, { "input_cost_per_token": 0.0000012, "output_cost_per_reasoning_token": 0.000012, "output_cost_per_token": 0.0000036, "range": [ 256000, 1000000 ] } ], "model_id": "dashscope/qwen-plus-2025-09-11", "model_name": "Qwen Plus (Sep 2025)", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012, "range": [ 0, 256000 ] }, { "input_cost_per_token": 0.0000012, "output_cost_per_reasoning_token": 0.000012, "output_cost_per_token": 0.0000036, "range": [ 256000, 1000000 ] } ], "model_id": "dashscope/qwen-plus-latest", "model_name": "Qwen Plus Latest", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 5e-7, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen-turbo", "model_name": "Qwen Turbo", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen-turbo-2024-11-01", "model_name": "Qwen Turbo (Nov 2024)", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 5e-7, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen-turbo-2025-04-28", "model_name": "Qwen Turbo (Apr 2025)", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 5e-7, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen-turbo-latest", "model_name": "Qwen Turbo Latest", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen3-30b-a3b", "model_name": "Qwen3 30B A3B", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015, "range": [ 0, 32000 ] }, { "cache_read_input_token_cost": 1.2e-7, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000025, "range": [ 32000, 128000 ] }, { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004, "range": [ 128000, 256000 ] }, { "cache_read_input_token_cost": 4e-7, "input_cost_per_token": 0.0000016, "output_cost_per_token": 0.0000096, "range": [ 256000, 1000000 ] } ], "model_id": "dashscope/qwen3-coder-flash", "model_name": "Qwen3 Coder Flash", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015, "range": [ 0, 32000 ] }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000025, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004, "range": [ 128000, 256000 ] }, { "input_cost_per_token": 0.0000016, "output_cost_per_token": 0.0000096, "range": [ 256000, 1000000 ] } ], "model_id": "dashscope/qwen3-coder-flash-2025-07-28", "model_name": "Qwen3 Coder Flash (Jul 2025)", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "range": [ 0, 32000 ] }, { "cache_read_input_token_cost": 1.8e-7, "input_cost_per_token": 0.0000018, "output_cost_per_token": 0.000009, "range": [ 32000, 128000 ] }, { "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 256000 ] }, { "cache_read_input_token_cost": 6e-7, "input_cost_per_token": 0.000006, "output_cost_per_token": 0.00006, "range": [ 256000, 1000000 ] } ], "model_id": "dashscope/qwen3-coder-plus", "model_name": "Qwen3 Coder Plus", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000018, "output_cost_per_token": 0.000009, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 256000 ] }, { "input_cost_per_token": 0.000006, "output_cost_per_token": 0.00006, "range": [ 256000, 1000000 ] } ], "model_id": "dashscope/qwen3-coder-plus-2025-07-22", "model_name": "Qwen3 Coder Plus (Jul 2025)", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 258048, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 252000 ] } ], "model_id": "dashscope/qwen3-max", "model_name": "Qwen3 Max", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 258048, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 252000 ] } ], "model_id": "dashscope/qwen3-max-2026-01-23", "model_name": "Qwen3 Max (Jan 2026)", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 258048, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 252000 ] } ], "model_id": "dashscope/qwen3-max-preview", "model_name": "Qwen3 Max Preview", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen3-next-80b-a3b-thinking", "model_name": "Qwen3 Next 80B A3B Thinking", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.15, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen3-vl-235b-a22b-thinking", "model_name": "Qwen3 Vl 235B A22B Thinking", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 1.6e-7, "output_cost_per_token": 0.00000287, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen3-vl-32b-thinking", "model_name": "Qwen3 Vl 32B Thinking", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.16, "output_cost_per_million": 2.87, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "max_input_tokens": 260096, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000016, "range": [ 0, 32000 ] }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000024, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000048, "range": [ 128000, 256000 ] } ], "model_id": "dashscope/qwen3-vl-plus", "model_name": "Qwen3 Vl Plus", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000024, "range": [ 0, 256000 ] }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "range": [ 256000, 1000000 ] } ], "model_id": "dashscope/qwen3.5-plus", "model_name": "Qwen3.5 Plus", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.0000075, "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen3.7-max", "model_name": "Qwen3.7 Max", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 2.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "range": [ 0, 256000 ] }, { "cache_read_input_token_cost": 2.4e-7, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000048, "range": [ 256000, 1000000 ] } ], "model_id": "dashscope/qwen3.7-plus", "model_name": "Qwen3.7 Plus", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 991808, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwen3.8-max", "model_name": "Qwen3.8 Max", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 98304, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "dashscope/qwq-plus", "model_name": "Qwq Plus", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000029999900000000002, "output_cost_per_token": 0.000015000020000000002, "max_input_tokens": 200000, "max_output_tokens": 128000, "deprecation_date": "2026-04-12", "input_dbu_cost_per_token": 0.000042857, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "model_id": "databricks-claude-3-7-sonnet", "model_name": "Databricks Claude 3 7 Sonnet", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 2.9999900000000004, "output_cost_per_million": 15.000020000000001, "cache_read_cost_per_token": 3.0002e-7, "cache_read_cost_per_million": 0.30002, "cache_write_cost_per_token": 0.00000374997, "cache_write_cost_per_million": 3.7499700000000002, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.00001000006, "output_cost_per_token": 0.00005000002, "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000142858, "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000714286, "prompt_cache_min_tokens": 512, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "thinking_always_on": true, "model_id": "databricks-claude-fable-5", "model_name": "Databricks Claude Fable 5", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 10.00006, "output_cost_per_million": 50.00002, "cache_read_cost_per_token": 0.00000100002, "cache_read_cost_per_million": 1.0000200000000001, "cache_write_cost_per_token": 0.00001250004, "cache_write_cost_per_million": 12.50004, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00001000006, "output_cost_per_token": 0.00005000002, "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000142858, "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000714286, "prompt_cache_min_tokens": 512, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_forced_tool_use": false, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "thinking_always_on": true, "model_id": "databricks-claude-fable-5-1", "model_name": "Databricks Claude Fable 5 1", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 10.00006, "output_cost_per_million": 50.00002, "cache_read_cost_per_token": 2.5004e-7, "cache_read_cost_per_million": 0.25004, "cache_write_cost_per_token": 0.00001250004, "cache_write_cost_per_million": 12.50004, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000100002, "output_cost_per_token": 0.00000500003, "max_input_tokens": 200000, "max_output_tokens": 64000, "input_dbu_cost_per_token": 0.000014286, "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000071429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 4096, "model_id": "databricks-claude-haiku-4-5", "model_name": "Databricks Claude Haiku 4 5", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 1.0000200000000001, "output_cost_per_million": 5.00003, "cache_read_cost_per_token": 1.0003e-7, "cache_read_cost_per_million": 0.10003000000000001, "cache_write_cost_per_token": 0.00000124999, "cache_write_cost_per_million": 1.24999, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000015000020000000002, "output_cost_per_token": 0.00007500003000000001, "max_input_tokens": 200000, "max_output_tokens": 32000, "input_dbu_cost_per_token": 0.000214286, "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.001071429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "databricks-claude-opus-4", "model_name": "Databricks Claude Opus 4", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 15.000020000000001, "output_cost_per_million": 75.00003000000001, "cache_read_cost_per_token": 0.00000150003, "cache_read_cost_per_million": 1.50003, "cache_write_cost_per_token": 0.00001874999, "cache_write_cost_per_million": 18.74999, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000015000020000000002, "output_cost_per_token": 0.00007500003000000001, "max_input_tokens": 200000, "max_output_tokens": 32000, "input_dbu_cost_per_token": 0.000214286, "max_tokens": 32000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.001071429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "databricks-claude-opus-4-1", "model_name": "Databricks Claude Opus 4 1", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 15.000020000000001, "output_cost_per_million": 75.00003000000001, "cache_read_cost_per_token": 0.00000150003, "cache_read_cost_per_million": 1.50003, "cache_write_cost_per_token": 0.00001874999, "cache_write_cost_per_million": 18.74999, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000500003, "output_cost_per_token": 0.000025000010000000002, "max_input_tokens": 200000, "max_output_tokens": 64000, "input_dbu_cost_per_token": 0.000071429, "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000357143, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096, "model_id": "databricks-claude-opus-4-5", "model_name": "Databricks Claude Opus 4 5", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 5.00003, "output_cost_per_million": 25.000010000000003, "cache_read_cost_per_token": 5.0001e-7, "cache_read_cost_per_million": 0.5000100000000001, "cache_write_cost_per_token": 0.00000625002, "cache_write_cost_per_million": 6.25002, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000500003, "output_cost_per_token": 0.000025000010000000002, "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000071429, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000357143, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_legacy_thinking": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 4096, "model_id": "databricks-claude-opus-4-6", "model_name": "Databricks Claude Opus 4 6", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 5.00003, "output_cost_per_million": 25.000010000000003, "cache_read_cost_per_token": 5.0001e-7, "cache_read_cost_per_million": 0.5000100000000001, "cache_write_cost_per_token": 0.00000625002, "cache_write_cost_per_million": 6.25002, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000500003, "output_cost_per_token": 0.00002500001, "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000071429, "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000357143, "prompt_cache_min_tokens": 2048, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "model_id": "databricks-claude-opus-4-7", "model_name": "Databricks Claude Opus 4 7", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 5.00003, "output_cost_per_million": 25.00001, "cache_read_cost_per_token": 5.0001e-7, "cache_read_cost_per_million": 0.5000100000000001, "cache_write_cost_per_token": 0.00000625002, "cache_write_cost_per_million": 6.25002, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000500003, "output_cost_per_token": 0.00002500001, "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000071429, "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000357143, "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "model_id": "databricks-claude-opus-4-8", "model_name": "Databricks Claude Opus 4 8", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 5.00003, "output_cost_per_million": 25.00001, "cache_read_cost_per_token": 5.0001e-7, "cache_read_cost_per_million": 0.5000100000000001, "cache_write_cost_per_token": 0.00000625002, "cache_write_cost_per_million": 6.25002, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000500003, "output_cost_per_token": 0.00002500001, "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000071429, "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000357143, "prompt_cache_min_tokens": 512, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "model_id": "databricks-claude-opus-5", "model_name": "Databricks Claude Opus 5", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 5.00003, "output_cost_per_million": 25.00001, "cache_read_cost_per_token": 5.0001e-7, "cache_read_cost_per_million": 0.5000100000000001, "cache_write_cost_per_token": 0.00000625002, "cache_write_cost_per_million": 6.25002, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000029999900000000002, "output_cost_per_token": 0.000015000020000000002, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-10-09", "input_dbu_cost_per_token": 0.000042857, "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000214286, "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "model_id": "databricks-claude-sonnet-4", "model_name": "Databricks Claude Sonnet 4", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 2.9999900000000004, "output_cost_per_million": 15.000020000000001, "cache_read_cost_per_token": 3.0002e-7, "cache_read_cost_per_million": 0.30002, "cache_write_cost_per_token": 0.00000374997, "cache_write_cost_per_million": 3.7499700000000002, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000029999900000000002, "output_cost_per_token": 0.000015000020000000002, "max_input_tokens": 200000, "max_output_tokens": 64000, "input_dbu_cost_per_token": 0.000042857, "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "model_id": "databricks-claude-sonnet-4-1", "model_name": "Databricks Claude Sonnet 4 1", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 2.9999900000000004, "output_cost_per_million": 15.000020000000001, "cache_read_cost_per_token": 3.0002e-7, "cache_read_cost_per_million": 0.30002, "cache_write_cost_per_token": 0.00000374997, "cache_write_cost_per_million": 3.7499700000000002, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000029999900000000002, "output_cost_per_token": 0.000015000020000000002, "max_input_tokens": 200000, "max_output_tokens": 64000, "input_dbu_cost_per_token": 0.000042857, "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "databricks-claude-sonnet-4-5", "model_name": "Databricks Claude Sonnet 4 5", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 2.9999900000000004, "output_cost_per_million": 15.000020000000001, "cache_read_cost_per_token": 3.0002e-7, "cache_read_cost_per_million": 0.30002, "cache_write_cost_per_token": 0.00000374997, "cache_write_cost_per_million": 3.7499700000000002, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000029999900000000002, "output_cost_per_token": 0.000015000020000000002, "max_input_tokens": 1000000, "max_output_tokens": 64000, "input_dbu_cost_per_token": 0.000042857, "max_tokens": 64000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_legacy_thinking": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "databricks-claude-sonnet-4-6", "model_name": "Databricks Claude Sonnet 4 6", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 2.9999900000000004, "output_cost_per_million": 15.000020000000001, "cache_read_cost_per_token": 3.0002e-7, "cache_read_cost_per_million": 0.30002, "cache_write_cost_per_token": 0.00000374997, "cache_write_cost_per_million": 3.7499700000000002, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000299999, "output_cost_per_token": 0.00001500002, "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000042857, "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. Introductory launch rates of 28.571 input / 142.857 output / 35.714 cache write / 2.857 cache read DBU run through 2026-08-31; the standard rates are listed here because entries carry no expiry date." }, "output_dbu_cost_per_token": 0.000214286, "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_mid_conversation_system": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_anthropic_thinking_payload": true, "supports_sampling_params": false, "supports_tool_choice": true, "model_id": "databricks-claude-sonnet-5", "model_name": "Databricks Claude Sonnet 5", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 2.99999, "output_cost_per_million": 15.00002, "cache_read_cost_per_token": 3.0002e-7, "cache_read_cost_per_million": 0.30002, "cache_write_cost_per_token": 0.00000374997, "cache_write_cost_per_million": 3.7499700000000002, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_dbu_cost_per_token": 0.000002, "max_tokens": 393216, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)." }, "output_dbu_cost_per_token": 0.000004, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-deepseek-v4-flash-0731", "model_name": "Databricks Deepseek V4 Flash 0731", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 0.14, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 1.4e-7, "cache_write_cost_per_million": 0.14, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.00000131999, "output_cost_per_token": 0.00000395997, "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_dbu_cost_per_token": 0.000018857, "max_tokens": 393216, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)." }, "output_dbu_cost_per_token": 0.000056571, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-deepseek-v4-pro-0813", "model_name": "Databricks Deepseek V4 Pro 0813", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 1.31999, "output_cost_per_million": 3.9599699999999998, "cache_read_cost_per_token": 1.3202e-7, "cache_read_cost_per_million": 0.13202, "cache_write_cost_per_token": 0.00000131999, "cache_write_cost_per_million": 1.31999, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000187502, "output_cost_per_token": 0.00001124998, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_dbu_cost_per_token": 0.000026786, "max_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000160714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gemini-3-5-flash", "model_name": "Databricks Gemini 3 5 Flash", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 1.87502, "output_cost_per_million": 11.249979999999999, "cache_read_cost_per_token": 1.8753e-7, "cache_read_cost_per_million": 0.18753, "cache_write_cost_per_token": 0.00000187502, "cache_write_cost_per_million": 1.87502, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3.7499e-7, "output_cost_per_token": 0.00000312501, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_dbu_cost_per_token": 0.000005357, "max_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000044643, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gemini-3-5-flash-lite", "model_name": "Databricks Gemini 3 5 Flash Lite", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 0.37499, "output_cost_per_million": 3.12501, "cache_read_cost_per_token": 3.752e-8, "cache_read_cost_per_million": 0.03752, "cache_write_cost_per_token": 3.7499e-7, "cache_write_cost_per_million": 0.37499, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000187502, "output_cost_per_token": 0.00000937503, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_dbu_cost_per_token": 0.000026786, "max_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000133929, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gemini-3-6-flash", "model_name": "Databricks Gemini 3 6 Flash", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 1.87502, "output_cost_per_million": 9.375029999999999, "cache_read_cost_per_token": 1.8753e-7, "cache_read_cost_per_million": 0.18753, "cache_write_cost_per_token": 0.00000187502, "cache_write_cost_per_million": 1.87502, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "metadata": { "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gemini-3-7-flash", "model_name": "Databricks Gemini 3 7 Flash", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "metadata": { "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." }, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gemini-3-8-flash", "model_name": "Databricks Gemini 3 8 Flash", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.00000439999, "max_input_tokens": 1000000, "max_output_tokens": 131072, "input_dbu_cost_per_token": 0.00002, "max_tokens": 131072, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference." }, "output_dbu_cost_per_token": 0.000062857, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-glm-5-2", "model_name": "Databricks Glm 5 2", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 1.4, "output_cost_per_million": 4.399990000000001, "cache_read_cost_per_token": 2.5998e-7, "cache_read_cost_per_million": 0.25998, "cache_write_cost_per_token": 0.0000014, "cache_write_cost_per_million": 1.4, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.00000439999, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_dbu_cost_per_token": 0.00002, "max_tokens": 65536, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000062857, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "thinking_always_on": true, "model_id": "databricks-glm-5-3", "model_name": "Databricks Glm 5 3", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 1.4, "output_cost_per_million": 4.399990000000001, "cache_read_cost_per_token": 2.5998e-7, "cache_read_cost_per_million": 0.25998, "cache_write_cost_per_token": 0.0000014, "cache_write_cost_per_million": 1.4, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 1.5001e-7, "output_cost_per_token": 5.0001e-7, "max_input_tokens": 1048576, "max_output_tokens": 131072, "input_dbu_cost_per_token": 0.000002143, "max_tokens": 131072, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000007143, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "thinking_always_on": true, "model_id": "databricks-glm-5-3-flash", "model_name": "Databricks Glm 5 3 Flash", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 0.15001, "output_cost_per_million": 0.5000100000000001, "cache_read_cost_per_token": 3.003e-8, "cache_read_cost_per_million": 0.030029999999999998, "cache_write_cost_per_token": 1.5001e-7, "cache_write_cost_per_million": 0.15001, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000249998, "output_cost_per_token": 0.000015000020000000002, "max_input_tokens": 922000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000035714, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gpt-5-4", "model_name": "Databricks GPT-5 4", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 2.49998, "output_cost_per_million": 15.000020000000001, "cache_read_cost_per_token": 2.4997e-7, "cache_read_cost_per_million": 0.24997, "cache_write_cost_per_token": 0.00000249998, "cache_write_cost_per_million": 2.49998, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 7.4998e-7, "output_cost_per_token": 0.00000450002, "max_input_tokens": 272000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000010714, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000064286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gpt-5-4-mini", "model_name": "Databricks GPT-5 4 Mini", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 0.74998, "output_cost_per_million": 4.50002, "cache_read_cost_per_token": 7.497e-8, "cache_read_cost_per_million": 0.07497000000000001, "cache_write_cost_per_token": 7.4998e-7, "cache_write_cost_per_million": 0.74998, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 1.9999e-7, "output_cost_per_token": 0.00000124999, "max_input_tokens": 272000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000002857, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000017857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gpt-5-4-nano", "model_name": "Databricks GPT-5 4 Nano", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 0.19999, "output_cost_per_million": 1.24999, "cache_read_cost_per_token": 2.002e-8, "cache_read_cost_per_million": 0.02002, "cache_write_cost_per_token": 1.9999e-7, "cache_write_cost_per_million": 0.19999, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000500003, "output_cost_per_token": 0.00002999997, "max_input_tokens": 922000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000071429, "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000428571, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gpt-5-5", "model_name": "Databricks GPT-5 5", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 5.00003, "output_cost_per_million": 29.999969999999998, "cache_read_cost_per_token": 5.0001e-7, "cache_read_cost_per_million": 0.5000100000000001, "cache_write_cost_per_token": 0.00000500003, "cache_write_cost_per_million": 5.00003, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00002999997, "output_cost_per_token": 0.00018000003, "max_input_tokens": 922000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000428571, "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.002571429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gpt-5-5-pro", "model_name": "Databricks GPT-5 5 Pro", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 29.999969999999998, "output_cost_per_million": 180.00003, "cache_read_cost_per_token": 0.00002999997, "cache_read_cost_per_million": 29.999969999999998, "cache_write_cost_per_token": 0.00002999997, "cache_write_cost_per_million": 29.999969999999998, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000100002, "output_cost_per_token": 0.00000599998, "max_input_tokens": 922000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000014286, "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000085714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gpt-5-6-luna", "model_name": "Databricks GPT-5 6 Luna", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 1.0000200000000001, "output_cost_per_million": 5.99998, "cache_read_cost_per_token": 1.0003e-7, "cache_read_cost_per_million": 0.10003000000000001, "cache_write_cost_per_token": 0.00000124999, "cache_write_cost_per_million": 1.24999, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000400001, "output_cost_per_token": 0.00001999998, "max_input_tokens": 922000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000057143, "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. Rates reflect OpenAI's promotional pricing in effect through November 21, 2026; afterwards input, cache and Batch rates are 25% higher and output rates 50% higher." }, "output_dbu_cost_per_token": 0.000285714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gpt-5-6-sol", "model_name": "Databricks GPT-5 6 Sol", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 4.00001, "output_cost_per_million": 19.99998, "cache_read_cost_per_token": 3.9998e-7, "cache_read_cost_per_million": 0.39998, "cache_write_cost_per_token": 0.00000500003, "cache_write_cost_per_million": 5.00003, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000249998, "output_cost_per_token": 0.00001500002, "max_input_tokens": 922000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000035714, "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gpt-5-6-terra", "model_name": "Databricks GPT-5 6 Terra", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 2.49998, "output_cost_per_million": 15.00002, "cache_read_cost_per_token": 2.4997e-7, "cache_read_cost_per_million": 0.24997, "cache_write_cost_per_token": 0.00000312501, "cache_write_cost_per_million": 3.12501, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.00000249998, "output_cost_per_token": 0.00000750001, "max_input_tokens": 500000, "input_dbu_cost_per_token": 0.000035714, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000107143, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-grok-4-6", "model_name": "Databricks Grok 4 6", "provider_id": "databricks", "provider_name": "Databricks", "max_output_tokens": 0, "input_cost_per_million": 2.49998, "output_cost_per_million": 7.50001, "cache_read_cost_per_token": 6.2503e-7, "cache_read_cost_per_million": 0.6250300000000001, "cache_write_cost_per_token": 0.00000249998, "cache_write_cost_per_million": 2.49998, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000100002, "output_cost_per_token": 0.00000404999, "max_input_tokens": 1000000, "input_dbu_cost_per_token": 0.000014286, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000057857, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "thinking_always_on": true, "model_id": "databricks-inkling", "model_name": "Databricks Inkling", "provider_id": "databricks", "provider_name": "Databricks", "max_output_tokens": 0, "input_cost_per_million": 1.0000200000000001, "output_cost_per_million": 4.04999, "cache_read_cost_per_token": 1.7003e-7, "cache_read_cost_per_million": 0.17003, "cache_write_cost_per_token": 0.00000100002, "cache_write_cost_per_million": 1.0000200000000001, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000299999, "output_cost_per_token": 0.00001500002, "max_input_tokens": 1000000, "max_output_tokens": 1048576, "input_dbu_cost_per_token": 0.000042857, "max_tokens": 1048576, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference." }, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-kimi-k3", "model_name": "Databricks Kimi K3", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 2.99999, "output_cost_per_million": 15.00002, "cache_read_cost_per_token": 3.0002e-7, "cache_read_cost_per_million": 0.30002, "cache_write_cost_per_token": 0.00000299999, "cache_write_cost_per_million": 2.99999, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 2.2001e-7, "output_cost_per_token": 0.00000220003, "max_input_tokens": 262144, "max_output_tokens": 25000, "input_dbu_cost_per_token": 0.000003143, "max_tokens": 25000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000031429, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "thinking_always_on": true, "model_id": "databricks-qwen35-122b-a10b", "model_name": "Databricks Qwen35 122B A10B", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 0.22000999999999998, "output_cost_per_million": 2.20003, "cache_read_cost_per_token": 2.2001e-7, "cache_read_cost_per_million": 0.22000999999999998, "cache_write_cost_per_token": 2.2001e-7, "cache_write_cost_per_million": 0.22000999999999998, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_tokens": 200000, "prompt_cache_min_tokens": 4096, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "anthropic/claude-haiku-4-5", "model_name": "Claude Haiku 4 5", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_tokens": 1000000, "prompt_cache_min_tokens": 2048, "source": "https://deepinfra.com/pricing", "supports_adaptive_thinking": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "model_id": "anthropic/claude-opus-4-7", "model_name": "Claude Opus 4 7", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 256000, "max_tokens": 256000, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "ByteDance/Seed-1.8", "model_name": "Seed 1.8", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 256000, "max_tokens": 256000, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "ByteDance/Seed-2.0-code", "model_name": "Seed 2.0 Code", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 256000, "max_tokens": 256000, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "ByteDance/Seed-2.0-mini", "model_name": "Seed 2.0 Mini", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 256000, "max_tokens": 256000, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "ByteDance/Seed-2.0-pro", "model_name": "Seed 2.0 Pro", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 9e-8, "output_cost_per_token": 1.8e-7, "max_input_tokens": 1048576, "max_tokens": 1048576, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "deepseek-ai/DeepSeek-V4-Flash", "model_name": "DeepSeek V4 Flash", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.09, "output_cost_per_million": 0.18, "cache_read_cost_per_token": 1.8e-8, "cache_read_cost_per_million": 0.018, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 8e-8, "output_cost_per_token": 1.8e-7, "max_input_tokens": 1048576, "max_tokens": 1048576, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "deepseek-ai/DeepSeek-V4-Flash-0731", "model_name": "DeepSeek V4 Flash 0731", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.08, "output_cost_per_million": 0.18, "cache_read_cost_per_token": 1.6e-8, "cache_read_cost_per_million": 0.016, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1000000, "max_tokens": 1000000, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "google/gemini-3.1-pro", "model_name": "Gemini 3.1 Pro", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7e-8, "output_cost_per_token": 3.4e-7, "max_input_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "google/gemma-4-26B-A4B-it", "model_name": "Gemma 4 26B A4B It", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.07, "output_cost_per_million": 0.33999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 3.8e-7, "max_input_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "google/gemma-4-31B-it", "model_name": "Gemma 4 31B It", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.13, "output_cost_per_million": 0.38, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 9e-8, "output_cost_per_token": 3.4e-7, "max_input_tokens": 262144, "max_tokens": 262144, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "google/gemma-4-31B-it-turbo", "model_name": "Gemma 4 31B It Turbo", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.09, "output_cost_per_million": 0.33999999999999997, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 7.6e-7, "max_input_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "google/gemma-4-31B-it-Ultra", "model_name": "Gemma 4 31B It Ultra", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.27, "output_cost_per_million": 0.76, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 2e-8, "output_cost_per_token": 1e-7, "max_input_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "google/gemma-4-E4B-it", "model_name": "Gemma 4 E4B It", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.02, "output_cost_per_million": 0.09999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 6e-8, "output_cost_per_token": 1.8e-7, "max_input_tokens": 131072, "max_tokens": 131072, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "inclusionAI/Ling-3.0-flash", "model_name": "Ling 3.0 Flash", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.06, "output_cost_per_million": 0.18, "cache_read_cost_per_token": 1.2e-8, "cache_read_cost_per_million": 0.012, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 131072, "max_tokens": 131072, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "meta-models/Muse-Glimmer-30B", "model_name": "Muse Glimmer 30B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 4e-8, "cache_read_cost_per_million": 0.04, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 3.8e-7, "output_cost_per_token": 0.0000017, "max_input_tokens": 196608, "max_tokens": 196608, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "MiniMaxAI/MiniMax-M2.7-Turbo", "model_name": "MiniMax M2.7 Turbo", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.38, "output_cost_per_million": 1.7, "cache_read_cost_per_token": 7e-8, "cache_read_cost_per_million": 0.07, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.8e-7, "output_cost_per_token": 0.0000011, "max_input_tokens": 524288, "max_tokens": 524288, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "MiniMaxAI/MiniMax-M3", "model_name": "MiniMax M3", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.28, "output_cost_per_million": 1.1, "cache_read_cost_per_token": 5.6e-8, "cache_read_cost_per_million": 0.056, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4.5e-7, "output_cost_per_token": 0.00000225, "max_input_tokens": 262144, "max_tokens": 262144, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "moonshotai/Kimi-K2.5", "model_name": "Kimi K2.5", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.44999999999999996, "output_cost_per_million": 2.25, "cache_read_cost_per_token": 7e-8, "cache_read_cost_per_million": 0.07, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 6.8e-7, "output_cost_per_token": 0.0000034, "max_input_tokens": 262144, "max_tokens": 262144, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "moonshotai/Kimi-K2.7-Code", "model_name": "Kimi K2.7 Code", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.6799999999999999, "output_cost_per_million": 3.4, "cache_read_cost_per_token": 1.36e-7, "cache_read_cost_per_million": 0.136, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 262144, "max_tokens": 262144, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "nvidia/Nemotron-3-Nano-30B-A3B", "model_name": "Nemotron 3 Nano 30B A3B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 8.5e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B", "model_name": "NVIDIA Nemotron 3 Super 120B A12B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.08499999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 262144, "max_tokens": 262144, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B", "model_name": "NVIDIA Nemotron 3 Ultra 550B A55B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.5, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 8e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 262144, "source": "https://deepinfra.com/pricing", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning", "model_name": "NVIDIA Nemotron 3.5 Lightning", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.08, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 4e-8, "cache_read_cost_per_million": 0.04, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "openai/gpt-oss-120b-Turbo", "model_name": "GPT Oss 120B Turbo", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 9.5e-7, "max_input_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "openai/gpt-oss-120b-Ultra", "model_name": "GPT Oss 120B Ultra", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.95, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.9e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "Qwen/Qwen3.5-122B-A10B", "model_name": "Qwen3.5 122B A10B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.29, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.6e-7, "output_cost_per_token": 0.0000026, "max_input_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "Qwen/Qwen3.5-27B", "model_name": "Qwen3.5 27B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.26, "output_cost_per_million": 2.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 262144, "max_tokens": 262144, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "Qwen/Qwen3.5-35B-A3B", "model_name": "Qwen3.5 35B A3B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.14, "output_cost_per_million": 1, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4.5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "max_tokens": 262144, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "Qwen/Qwen3.5-397B-A17B", "model_name": "Qwen3.5 397B A17B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.44999999999999996, "output_cost_per_million": 3, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3.2e-7, "output_cost_per_token": 0.0000032, "max_input_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "Qwen/Qwen3.6-27B", "model_name": "Qwen3.6 27B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.32, "output_cost_per_million": 3.1999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 9.5e-7, "max_input_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "Qwen/Qwen3.6-35B-A3B", "model_name": "Qwen3.6 35B A3B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.95, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 262144, "max_tokens": 262144, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "Qwen/Qwen3.8-2.4T-A95B", "model_name": "Qwen3.8 2.4T A95B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "max_tokens": 262144, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "Qwen/Qwen3.8-27B", "model_name": "Qwen3.8 27B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 3, "cache_read_cost_per_token": 4e-8, "cache_read_cost_per_million": 0.04, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 5.8e-7, "max_input_tokens": 262144, "max_tokens": 262144, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "tencent/Hy3", "model_name": "Hy3", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.14, "output_cost_per_million": 0.58, "cache_read_cost_per_token": 3.5e-8, "cache_read_cost_per_million": 0.035, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.00000405, "max_input_tokens": 524288, "max_tokens": 524288, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "thinkingmachines/Inkling", "model_name": "Inkling", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.95, "output_cost_per_million": 4.05, "cache_read_cost_per_token": 1.6e-7, "cache_read_cost_per_million": 0.16, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4.5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 524288, "max_tokens": 524288, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "thinkingmachines/Inkling-Small", "model_name": "Inkling Small", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.44999999999999996, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 262144, "max_tokens": 262144, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "XiaomiMiMo/MiMo-V2.5", "model_name": "MiMo V2.5", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 2, "cache_read_cost_per_token": 8e-8, "cache_read_cost_per_million": 0.08, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 1048576, "max_tokens": 1048576, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "XiaomiMiMo/MiMo-V2.5-Pro", "model_name": "MiMo V2.5 Pro", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 1, "output_cost_per_million": 3, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 202752, "max_tokens": 202752, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "zai-org/GLM-4.6", "model_name": "GLM 4.6", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.5, "output_cost_per_million": 2, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.00000175, "max_input_tokens": 202752, "max_tokens": 202752, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "zai-org/GLM-4.7", "model_name": "GLM 4.7", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.75, "cache_read_cost_per_token": 8e-8, "cache_read_cost_per_million": 0.08, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 6e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 202752, "max_tokens": 202752, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "zai-org/GLM-4.7-Flash", "model_name": "GLM 4.7 Flash", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.06, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 1048576, "max_tokens": 1048576, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://deepinfra.com/pricing", "model_id": "zai-org/GLM-5.2", "model_name": "GLM 5.2", "provider_id": "deepinfra", "provider_name": "DeepInfra", "max_output_tokens": 0, "input_cost_per_million": 0.75, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token_cache_hit": 6e-9, "max_tokens": 393216, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "deepseek-flash", "model_name": "Deepseek Flash", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-9, "cache_read_cost_per_million": 0.006, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_response_schema": true, "input_cost_per_token": 2.8e-7, "output_cost_per_token": 4.2e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "model_id": "deepseek-reasoner", "model_name": "Deepseek Reasoner", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.28, "output_cost_per_million": 0.42, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token_cache_hit": 6e-9, "max_tokens": 393216, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "deepseek-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-9, "cache_read_cost_per_million": 0.006, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token_cache_hit": 6e-9, "max_tokens": 393216, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "deepseek-v4-flash-vision-exp", "model_name": "Deepseek V4 Flash Vision Exp", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-9, "cache_read_cost_per_million": 0.006, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.00000132, "output_cost_per_token": 0.00000396, "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token_cache_hit": 4.4e-8, "max_tokens": 393216, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "deepseek-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 1.32, "output_cost_per_million": 3.9600000000000004, "cache_read_cost_per_token": 4.4e-8, "cache_read_cost_per_million": 0.044, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token_cache_hit": 6e-9, "max_tokens": 393216, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "deepseek/deepseek-flash", "model_name": "Deepseek Flash", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-9, "cache_read_cost_per_million": 0.006, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.00000219, "max_input_tokens": 65536, "max_output_tokens": 8192, "input_cost_per_token_cache_hit": 1.4e-7, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "deepseek/deepseek-r1", "model_name": "DeepSeek R1", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.55, "output_cost_per_million": 2.1900000000000004, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_response_schema": true, "input_cost_per_token": 2.8e-7, "output_cost_per_token": 4.2e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "input_cost_per_token_cache_hit": 2.8e-8, "max_tokens": 65536, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "model_id": "deepseek/deepseek-reasoner", "model_name": "Deepseek Reasoner", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.28, "output_cost_per_million": 0.42, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false, "supports_vision": false }, { "supports_function_calling": true, "input_cost_per_token": 2.8e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token_cache_hit": 2.8e-8, "max_tokens": 163840, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "deepseek/deepseek-v3.2", "model_name": "Deepseek V3.2", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.28, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token_cache_hit": 6e-9, "max_tokens": 393216, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "deepseek/deepseek-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-9, "cache_read_cost_per_million": 0.006, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token_cache_hit": 6e-9, "max_tokens": 393216, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "deepseek/deepseek-v4-flash-vision-exp", "model_name": "Deepseek V4 Flash Vision Exp", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-9, "cache_read_cost_per_million": 0.006, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.00000132, "output_cost_per_token": 0.00000396, "max_input_tokens": 1000000, "max_output_tokens": 393216, "input_cost_per_token_cache_hit": 4.4e-8, "max_tokens": 393216, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "deepseek/deepseek-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 1.32, "output_cost_per_million": 3.9600000000000004, "cache_read_cost_per_token": 4.4e-8, "cache_read_cost_per_million": 0.044, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_response_schema": true, "input_cost_per_token": 5.6e-7, "output_cost_per_token": 0.00000168, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://fireworks.ai/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/deepseek-v3p1", "model_name": "Deepseek V3p1", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.56, "output_cost_per_million": 1.68, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_function_calling": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_response_schema": true, "input_cost_per_token": 5.6e-7, "output_cost_per_token": 0.00000168, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://fireworks.ai/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus", "model_name": "Deepseek V3p1 Terminus", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.56, "output_cost_per_million": 1.68, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_function_calling": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 5.6e-7, "output_cost_per_token": 0.00000168, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "source": "https://fireworks.ai/models/fireworks/deepseek-v3p2", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/deepseek-v3p2", "model_name": "Deepseek V3p2", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.56, "output_cost_per_million": 1.68, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.14, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 6.6e-7, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731", "model_name": "Deepseek V4 Flash 0731", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.22, "output_cost_per_million": 0.66, "cache_read_cost_per_token": 7e-9, "cache_read_cost_per_million": 0.007, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.00000174, "output_cost_per_token": 0.00000348, "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 1.74, "output_cost_per_million": 3.48, "cache_read_cost_per_token": 1.45e-7, "cache_read_cost_per_million": 0.145, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.00000132, "output_cost_per_token": 0.00000396, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813", "model_name": "Deepseek V4 Pro 0813", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 1.32, "output_cost_per_million": 3.9600000000000004, "cache_read_cost_per_token": 4.4e-8, "cache_read_cost_per_million": 0.044, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 6.6e-7, "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash", "model_name": "Deepseek V4p1 Flash", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.22, "output_cost_per_million": 0.66, "cache_read_cost_per_token": 7e-9, "cache_read_cost_per_million": 0.007, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.00000219, "max_input_tokens": 128000, "max_output_tokens": 96000, "max_tokens": 96000, "source": "https://fireworks.ai/models/fireworks/glm-4p5", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/glm-4p5", "model_name": "Glm 4p5", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.55, "output_cost_per_million": 2.1900000000000004, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 8.8e-7, "max_input_tokens": 128000, "max_output_tokens": 96000, "max_tokens": 96000, "source": "https://artificialanalysis.ai/models/glm-4-5-air", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/glm-4p5-air", "model_name": "Glm 4p5 Air", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.22, "output_cost_per_million": 0.88, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "model_id": "fireworks_ai/accounts/fireworks/models/glm-4p5v", "model_name": "Glm 4p5v", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 1.2, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.00000219, "max_input_tokens": 202800, "max_output_tokens": 202800, "max_tokens": 202800, "source": "https://fireworks.ai/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/glm-4p6", "model_name": "Glm 4p6", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.55, "output_cost_per_million": 2.1900000000000004, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 202800, "max_output_tokens": 202800, "max_tokens": 202800, "source": "https://fireworks.ai/models/fireworks/glm-4p7", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/glm-4p7", "model_name": "Glm 4p7", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 202800, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/glm-5p1", "model_name": "Glm 5p1", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/glm-5p2", "model_name": "Glm 5p2", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1048576, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/glm-5p3", "model_name": "Glm 5p3", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 1.5e-8, "cache_read_cost_per_million": 0.015, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 7e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/gpt-oss-20b", "model_name": "GPT Oss 20B", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.07, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 3.5e-8, "cache_read_cost_per_million": 0.035, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/kimi-k2p6", "model_name": "Kimi K2p6", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.6e-7, "cache_read_cost_per_million": 0.16, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/kimi-k2p7-code", "model_name": "Kimi K2p7 Code", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.9e-7, "cache_read_cost_per_million": 0.19, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/kimi-k3", "model_name": "Kimi K3", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 196608, "max_output_tokens": 196608, "max_tokens": 196608, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/minimax-m2p7", "model_name": "Minimax M2p7", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 512000, "max_output_tokens": 512000, "max_tokens": 512000, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/minimax-m3", "model_name": "Minimax M3", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/muse-glimmer-30b", "model_name": "Muse Glimmer 30B", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.35, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 4e-8, "cache_read_cost_per_million": 0.04, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4", "model_name": "Nemotron 3 Ultra Nvfp4", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 1.2e-7, "cache_read_cost_per_million": 0.12, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b", "model_name": "Nemotron Lightning 3p5 30B A3B", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "model_id": "fireworks_ai/accounts/fireworks/models/qwen3-32b", "model_name": "Qwen3 32B", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.8999999999999999, "output_cost_per_million": 0.8999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 40960, "max_output_tokens": 40960, "max_tokens": 40960, "supports_reasoning": true, "model_id": "fireworks_ai/accounts/fireworks/models/qwen3-8b", "model_name": "Qwen3 8B", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 4.5e-7, "output_cost_per_token": 0.0000018, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "model_id": "fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct", "model_name": "Qwen3 Coder 480B A35B Instruct", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.44999999999999996, "output_cost_per_million": 1.7999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/qwen3p7-plus", "model_name": "Qwen3p7 Plus", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "cache_read_cost_per_token": 8e-8, "cache_read_cost_per_million": 0.08, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 262144, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/qwen3p8-max", "model_name": "Qwen3p8 Max", "provider_id": "fireworks", "provider_name": "Fireworks AI", "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000028, "output_cost_per_token": 0.0000088, "max_input_tokens": 202800, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/routers/glm-5p1-fast", "model_name": "Glm 5p1 Fast", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 2.8, "output_cost_per_million": 8.8, "cache_read_cost_per_token": 5.2e-7, "cache_read_cost_per_million": 0.52, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000021, "output_cost_per_token": 0.0000066, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/routers/glm-5p2-fast", "model_name": "Glm 5p2 Fast", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 2.0999999999999996, "output_cost_per_million": 6.6000000000000005, "cache_read_cost_per_token": 2.1e-7, "cache_read_cost_per_million": 0.21, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000021, "output_cost_per_token": 0.0000066, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/routers/glm-5p2-fast-us", "model_name": "Glm 5p2 Fast Us", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 2.0999999999999996, "output_cost_per_million": 6.6000000000000005, "cache_read_cost_per_token": 2.1e-7, "cache_read_cost_per_million": 0.21, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/routers/kimi-k2p6-fast", "model_name": "Kimi K2p6 Fast", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000019, "output_cost_per_token": 0.000008, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/routers/kimi-k2p7-code-fast", "model_name": "Kimi K2p7 Code Fast", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 1.9, "output_cost_per_million": 8, "cache_read_cost_per_token": 3.8e-7, "cache_read_cost_per_million": 0.38, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000045, "output_cost_per_token": 0.0000225, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/routers/kimi-k3-fast", "model_name": "Kimi K3 Fast", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 4.5, "output_cost_per_million": 22.5, "cache_read_cost_per_token": 4.5e-7, "cache_read_cost_per_million": 0.44999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/routers/kimi-k3-us", "model_name": "Kimi K3 Us", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/deepseek-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.14, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 6.6e-7, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/deepseek-v4-flash-0731", "model_name": "Deepseek V4 Flash 0731", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.22, "output_cost_per_million": 0.66, "cache_read_cost_per_token": 7e-9, "cache_read_cost_per_million": 0.007, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.00000174, "output_cost_per_token": 0.00000348, "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/deepseek-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 1.74, "output_cost_per_million": 3.48, "cache_read_cost_per_token": 1.45e-7, "cache_read_cost_per_million": 0.145, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 6.6e-7, "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/deepseek-v4p1-flash", "model_name": "Deepseek V4p1 Flash", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.22, "output_cost_per_million": 0.66, "cache_read_cost_per_token": 7e-9, "cache_read_cost_per_million": 0.007, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 202800, "max_output_tokens": 202800, "max_tokens": 202800, "source": "https://fireworks.ai/models/fireworks/glm-4p7", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/glm-4p7", "model_name": "Glm 4p7", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 202800, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/glm-5p1", "model_name": "Glm 5p1", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000028, "output_cost_per_token": 0.0000088, "max_input_tokens": 202800, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/glm-5p1-fast", "model_name": "Glm 5p1 Fast", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 2.8, "output_cost_per_million": 8.8, "cache_read_cost_per_token": 5.2e-7, "cache_read_cost_per_million": 0.52, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/glm-5p2", "model_name": "Glm 5p2", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000021, "output_cost_per_token": 0.0000066, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/glm-5p2-fast", "model_name": "Glm 5p2 Fast", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 2.0999999999999996, "output_cost_per_million": 6.6000000000000005, "cache_read_cost_per_token": 2.1e-7, "cache_read_cost_per_million": 0.21, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000021, "output_cost_per_token": 0.0000066, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/glm-5p2-fast-us", "model_name": "Glm 5p2 Fast Us", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 2.0999999999999996, "output_cost_per_million": 6.6000000000000005, "cache_read_cost_per_token": 2.1e-7, "cache_read_cost_per_million": 0.21, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 1.5e-8, "cache_read_cost_per_million": 0.015, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 7e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/gpt-oss-20b", "model_name": "GPT Oss 20B", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.07, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 3.5e-8, "cache_read_cost_per_million": 0.035, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/kimi-k2p6", "model_name": "Kimi K2p6", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.6e-7, "cache_read_cost_per_million": 0.16, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/kimi-k2p6-fast", "model_name": "Kimi K2p6 Fast", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/kimi-k2p7-code", "model_name": "Kimi K2p7 Code", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.9e-7, "cache_read_cost_per_million": 0.19, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000019, "output_cost_per_token": 0.000008, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/kimi-k2p7-code-fast", "model_name": "Kimi K2p7 Code Fast", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 1.9, "output_cost_per_million": 8, "cache_read_cost_per_token": 3.8e-7, "cache_read_cost_per_million": 0.38, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/kimi-k3", "model_name": "Kimi K3", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000045, "output_cost_per_token": 0.0000225, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/kimi-k3-fast", "model_name": "Kimi K3 Fast", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 4.5, "output_cost_per_million": 22.5, "cache_read_cost_per_token": 4.5e-7, "cache_read_cost_per_million": 0.44999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/kimi-k3-us", "model_name": "Kimi K3 Us", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 196608, "max_output_tokens": 196608, "max_tokens": 196608, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/minimax-m2p7", "model_name": "Minimax M2p7", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 512000, "max_output_tokens": 512000, "max_tokens": 512000, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/minimax-m3", "model_name": "Minimax M3", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/muse-glimmer-30b", "model_name": "Muse Glimmer 30B", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.35, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 4e-8, "cache_read_cost_per_million": 0.04, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/nemotron-3-ultra-nvfp4", "model_name": "Nemotron 3 Ultra Nvfp4", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 1.2e-7, "cache_read_cost_per_million": 0.12, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/nemotron-lightning-3p5-30b-a3b", "model_name": "Nemotron Lightning 3p5 30B A3B", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/qwen3p7-plus", "model_name": "Qwen3p7 Plus", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "cache_read_cost_per_token": 8e-8, "cache_read_cost_per_million": 0.08, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 262144, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "fireworks_ai/qwen3p8-max", "model_name": "Qwen3p8 Max", "provider_id": "fireworks", "provider_name": "Fireworks AI", "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_prompt_caching": true, "supports_reasoning": true, "reasoning_effort_levels": [], "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_image_input": false, "supports_video_input": false, "comment": "DeepSeek chat model for instruction following, coding, and analysis", "source": "https://api.friendli.ai/serverless/v1/models", "model_id": "friendliai/deepseek-ai/DeepSeek-V3.2", "model_name": "DeepSeek V3.2", "provider_id": "friendliai", "provider_name": "Friendliai", "input_cost_per_million": 0.5, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_prompt_caching": false, "supports_reasoning": true, "reasoning_effort_levels": [], "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_image_input": true, "supports_video_input": false, "comment": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning", "source": "https://api.friendli.ai/serverless/v1/models", "model_id": "friendliai/google/gemma-4-31B-it", "model_name": "Gemma 4 31B It", "provider_id": "friendliai", "provider_name": "Friendliai", "input_cost_per_million": 0.14, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 262144, "max_output_tokens": 262144, "deprecation_date": "2026-09-06", "max_tokens": 262144, "supports_prompt_caching": true, "supports_reasoning": true, "reasoning_effort_levels": [], "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_image_input": false, "supports_video_input": false, "comment": "Frontier-scale multilingual language model developed by LG AI Research", "source": "https://api.friendli.ai/serverless/v1/models", "model_id": "friendliai/LGAI-EXAONE/K-EXAONE-2.0-750B-A37B", "model_name": "K EXAONE 2.0 750B A37B", "provider_id": "friendliai", "provider_name": "Friendliai", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 1.2e-7, "cache_read_cost_per_million": 0.12, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 196608, "max_output_tokens": 196608, "max_tokens": 196608, "supports_prompt_caching": true, "supports_reasoning": true, "reasoning_effort_levels": [], "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_image_input": false, "supports_video_input": false, "comment": "Prior MiniMax coding model for agent workflows, office edits, and automation", "source": "https://api.friendli.ai/serverless/v1/models", "model_id": "friendliai/MiniMaxAI/MiniMax-M2.5", "model_name": "MiniMax M2.5", "provider_id": "friendliai", "provider_name": "Friendliai", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 202752, "max_output_tokens": 202752, "max_tokens": 202752, "supports_prompt_caching": true, "supports_reasoning": true, "reasoning_effort_levels": [], "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_image_input": false, "supports_video_input": false, "comment": "Strong GLM coding model for agentic engineering, terminals, and repository generation", "source": "https://api.friendli.ai/serverless/v1/models", "model_id": "friendliai/zai-org/GLM-5.1", "model_name": "GLM 5.1", "provider_id": "friendliai", "provider_name": "Friendliai", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "supports_prompt_caching": true, "supports_reasoning": true, "reasoning_effort_levels": [ "high", "max" ], "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_image_input": false, "supports_video_input": false, "comment": "Open flagship GLM for long-horizon coding agents and million-token context work", "source": "https://api.friendli.ai/serverless/v1/models", "model_id": "friendliai/zai-org/GLM-5.2", "model_name": "GLM 5.2", "provider_id": "friendliai", "provider_name": "Friendliai", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.00000126, "output_cost_per_token": 0.00000396, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "supports_prompt_caching": true, "supports_reasoning": true, "reasoning_effort_levels": [ "low", "high", "max" ], "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_image_input": false, "supports_video_input": false, "comment": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "source": "https://api.friendli.ai/serverless/v1/models", "model_id": "friendliai/zai-org/GLM-5.3", "model_name": "GLM 5.3", "provider_id": "friendliai", "provider_name": "Friendliai", "input_cost_per_million": 1.26, "output_cost_per_million": 3.9600000000000004, "cache_read_cost_per_token": 2.34e-7, "cache_read_cost_per_million": 0.234, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "supports_prompt_caching": true, "supports_reasoning": true, "reasoning_effort_levels": [ "low", "high", "max" ], "supports_native_structured_output": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_image_input": true, "supports_video_input": true, "comment": "Native multimodal GLM model for efficient coding and long-horizon agent tasks", "source": "https://api.friendli.ai/serverless/v1/models", "model_id": "friendliai/zai-org/GLM-5.3-Flash", "model_name": "GLM 5.3 Flash", "provider_id": "friendliai", "provider_name": "Friendliai", "input_cost_per_million": 0.15, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false, "model_id": "2.5-flash", "model_name": "2.5 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 3e-7, "max_tokens": 65535, "output_cost_per_reasoning_token": 4e-7, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false, "model_id": "2.5-flash-lite", "model_name": "2.5 Flash Lite", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2025-11-18", "input_cost_per_audio_token": 5e-7, "max_tokens": 65535, "output_cost_per_reasoning_token": 4e-7, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false, "model_id": "2.5-flash-lite-preview-06-17", "model_name": "2.5 Flash Lite Preview 06 17", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2026-03-31", "input_cost_per_audio_token": 3e-7, "max_tokens": 65535, "output_cost_per_reasoning_token": 4e-7, "rpm": 15, "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false, "model_id": "2.5-flash-lite-preview-09-2025", "model_name": "2.5 Flash Lite Preview 09 2025", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2026-02-17", "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false, "model_id": "2.5-flash-preview-09-2025", "model_name": "2.5 Flash Preview 09 2025", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_priority": 0.00000125, "input_cost_per_token_above_200k_tokens_priority": 0.0000025, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000015, "output_cost_per_token_priority": 0.00001, "output_cost_per_token_above_200k_tokens_priority": 0.000015, "rpm": 2000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "model_id": "2.5-pro", "model_name": "2.5 Pro", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.000003, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 9e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000054, "cache_read_input_token_cost_priority": 9e-8, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "3-flash-preview", "model_name": "3 Flash Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2026-03-09", "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "tpm": 800000, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "model_id": "3-pro-preview", "model_name": "3 Pro Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "deprecation_date": "2027-05-07", "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "3.1-flash-lite", "model_name": "3.1 Flash Lite", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "deprecation_date": "2026-05-25", "input_cost_per_audio_token": 5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "3.1-flash-lite-preview", "model_name": "3.1 Flash Lite Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "3.1-pro-preview", "model_name": "3.1 Pro Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "3.1-pro-preview-customtools", "model_name": "3.1 Pro Preview Customtools", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000009, "max_input_tokens": 1048576, "max_output_tokens": 65535, "prompt_cache_min_tokens": 4096, "input_cost_per_audio_token": 0.0000015, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.000009, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000027, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-7, "output_cost_per_token_batches": 0.0000045, "input_cost_per_token_flex": 7.5e-7, "output_cost_per_token_flex": 0.0000045, "cache_read_input_token_cost_flex": 8e-8, "model_id": "3.5-flash", "model_name": "3.5 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 1.5, "output_cost_per_million": 9, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_token_cost_flex": 2e-8, "cache_read_input_token_cost_priority": 5e-8, "input_cost_per_token_batches": 1.5e-7, "input_cost_per_token_flex": 1.5e-7, "input_cost_per_token_priority": 5.4e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token_batches": 0.00000125, "output_cost_per_token_flex": 0.00000125, "output_cost_per_token_priority": 0.0000045, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "3.5-flash-lite", "model_name": "3.5 Flash Lite", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.00000135, "output_cost_per_token_priority": 0.00000675, "cache_read_input_token_cost_priority": 1.35e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "3.6-flash", "model_name": "3.6 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.00000135, "output_cost_per_token_priority": 0.00000675, "cache_read_input_token_cost_priority": 1.35e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "3.7-flash", "model_name": "3.7 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.00000135, "output_cost_per_token_priority": 0.00000675, "cache_read_input_token_cost_priority": 1.35e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "3.8-flash", "model_name": "3.8 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "model_id": "flash-latest", "model_name": "Flash Latest", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 3e-7, "max_tokens": 65535, "output_cost_per_reasoning_token": 4e-7, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "model_id": "flash-lite-latest", "model_name": "Flash Lite Latest", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "model_id": "gemini-exp-1206", "model_name": "Gemini Exp (Jun 2012)", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "model_id": "gemini-flash-latest", "model_name": "Gemini Flash Latest", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 3e-7, "max_tokens": 65535, "output_cost_per_reasoning_token": 4e-7, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "model_id": "gemini-flash-lite-latest", "model_name": "Gemini Flash Lite Latest", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 2000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "model_id": "gemini-pro-latest", "model_name": "Gemini Pro Latest", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://ai.google.dev/gemini-api/docs/pricing", "model_id": "gemma-4-26b-a4b-it", "model_name": "Gemma 4 26B A4B It", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://ai.google.dev/gemini-api/docs/pricing", "model_id": "gemma-4-31b-it", "model_name": "Gemma 4 31B It", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000009, "max_input_tokens": 131072, "max_output_tokens": 65536, "input_cost_per_audio_token": 0.0000015, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.000009, "output_cost_per_video_token": 0.0000175, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1beta/interactions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "video" ], "supports_audio_input": true, "supports_reasoning": true, "supports_system_messages": true, "supports_video_input": true, "tpm": 800000, "model_id": "omni-1.1-flash", "model_name": "Omni 1.1 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 1.5, "output_cost_per_million": 9, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000009, "max_input_tokens": 131072, "max_output_tokens": 65536, "deprecation_date": "2026-09-30", "input_cost_per_audio_token": 0.0000015, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.000009, "output_cost_per_video_token": 0.0000175, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1beta/interactions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "video" ], "supports_audio_input": true, "supports_reasoning": true, "supports_system_messages": true, "supports_video_input": true, "tpm": 800000, "model_id": "omni-flash-preview", "model_name": "Omni Flash Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 1.5, "output_cost_per_million": 9, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 2000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "model_id": "pro-latest", "model_name": "Pro Latest", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2026-04-30", "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 250000, "rpm": 10, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "model_id": "robotics-er-1.5-preview", "model_name": "Robotics Er 1.5 Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 131072, "max_output_tokens": 65536, "deprecation_date": "2026-08-31", "input_cost_per_audio_token": 0.000002, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.000005, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "web_search_billing_unit": "per_query", "model_id": "robotics-er-1.6-preview", "model_name": "Robotics Er 1.6 Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 131072, "max_output_tokens": 65536, "input_cost_per_audio_token": 0.000002, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00001, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "web_search_billing_unit": "per_query", "model_id": "robotics-er-2-preview", "model_name": "Robotics Er 2 Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "search_context_cost_per_query": { "search_context_size_high": 0.005, "search_context_size_low": 0.005, "search_context_size_medium": 0.005 }, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openai/gpt-oss-safeguard-20b", "model_name": "GPT Oss Safeguard 20B", "provider_id": "groq", "provider_name": "Groq", "input_cost_per_million": 0.075, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 3.7e-8, "cache_read_cost_per_million": 0.037, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 2.9e-7, "output_cost_per_token": 5.9e-7, "max_input_tokens": 131000, "max_output_tokens": 131000, "deprecation_date": "2026-07-17", "max_tokens": 131000, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen/qwen3-32b", "model_name": "Qwen3 32B", "provider_id": "groq", "provider_name": "Groq", "input_cost_per_million": 0.29, "output_cost_per_million": 0.59, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://console.groq.com/docs/model/qwen/qwen3.6-27b", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen/qwen3.6-27b", "model_name": "Qwen3.6 27B", "provider_id": "groq", "provider_name": "Groq", "input_cost_per_million": 0.6, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 131042, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://console.groq.com/docs/model/qwen/qwen3.8-27b", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen/qwen3.8-27b", "model_name": "Qwen3.8 27B", "provider_id": "groq", "provider_name": "Groq", "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/deepseek-llama3.3-70b", "model_name": "Deepseek Llama3.3 70B", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/deepseek-r1-0528", "model_name": "Deepseek R1 0528", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/deepseek-r1-671b", "model_name": "Deepseek R1 671B", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 0.7999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 1e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/qwen3-32b-fp8", "model_name": "Qwen3 32B Fp8", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.09999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000175, "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://docs.libertai.io/apis/text/", "model_id": "libertai/deepseek-v4-flash-thinking", "model_name": "Deepseek V4 Flash Thinking", "provider_id": "libertai", "provider_name": "Libertai", "input_cost_per_million": 0.25, "output_cost_per_million": 1.75, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://docs.libertai.io/apis/text/", "model_id": "libertai/gemma-4-31b-it-thinking", "model_name": "Gemma 4 31B It Thinking", "provider_id": "libertai", "provider_name": "Libertai", "input_cost_per_million": 0.15, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000175, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://docs.libertai.io/apis/text/", "model_id": "libertai/qwen3.5-122b-a10b-thinking", "model_name": "Qwen3.5 122B A10B Thinking", "provider_id": "libertai", "provider_name": "Libertai", "input_cost_per_million": 0.25, "output_cost_per_million": 1.75, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://docs.libertai.io/apis/text/", "model_id": "libertai/qwen3.6-27b-thinking", "model_name": "Qwen3.6 27B Thinking", "provider_id": "libertai", "provider_name": "Libertai", "input_cost_per_million": 0.15, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://docs.libertai.io/apis/text/", "model_id": "libertai/qwen3.6-35b-a3b-thinking", "model_name": "Qwen3.6 35B A3B Thinking", "provider_id": "libertai", "provider_name": "Libertai", "input_cost_per_million": 0.15, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 8e-8, "output_cost_per_token": 1.5e-7, "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "supports_reasoning": true, "model_id": "llamagate/deepseek-r1-7b-qwen", "model_name": "Deepseek R1 7B Qwen", "provider_id": "llamagate", "provider_name": "Llamagate", "input_cost_per_million": 0.08, "output_cost_per_million": 0.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 65536, "max_output_tokens": 16384, "max_tokens": 16384, "supports_reasoning": true, "model_id": "llamagate/deepseek-r1-8b", "model_name": "Deepseek R1 8B", "provider_id": "llamagate", "provider_name": "Llamagate", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 8e-8, "output_cost_per_token": 1.5e-7, "max_input_tokens": 32768, "max_output_tokens": 8192, "max_tokens": 8192, "supports_reasoning": true, "model_id": "llamagate/openthinker-7b", "model_name": "Openthinker 7B", "provider_id": "llamagate", "provider_name": "Llamagate", "input_cost_per_million": 0.08, "output_cost_per_million": 0.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00000425, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "meta/muse-spark-1.1", "model_name": "Muse Spark 1.1", "provider_id": "meta", "provider_name": "Meta", "input_cost_per_million": 1.25, "output_cost_per_million": 4.25, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00000425, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "meta/muse-spark-1.2", "model_name": "Muse Spark 1.2", "provider_id": "meta", "provider_name": "Meta", "input_cost_per_million": 1.25, "output_cost_per_million": 4.25, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "meta/muse-spark-1.2-contributor", "model_name": "Muse Spark 1.2 Contributor", "provider_id": "meta", "provider_name": "Meta", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 2e-9, "cache_read_cost_per_million": 0.002, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00000425, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "meta/muse-spark-1.3", "model_name": "Muse Spark 1.3", "provider_id": "meta", "provider_name": "Meta", "input_cost_per_million": 1.25, "output_cost_per_million": 4.25, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "meta/muse-spark-1.3-contributor", "model_name": "Muse Spark 1.3 Contributor", "provider_id": "meta", "provider_name": "Meta", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 2e-9, "cache_read_cost_per_million": 0.002, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 200000, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "model_id": "minimax/MiniMax-M2", "model_name": "MiniMax M2", "provider_id": "minimax", "provider_name": "MiniMax", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "model_id": "minimax/MiniMax-M2.1", "model_name": "MiniMax M2.1", "provider_id": "minimax", "provider_name": "MiniMax", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 1000000, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "model_id": "minimax/MiniMax-M2.1-lightning", "model_name": "MiniMax M2.1 Lightning", "provider_id": "minimax", "provider_name": "MiniMax", "input_cost_per_million": 0.3, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "model_id": "minimax/MiniMax-M2.5", "model_name": "MiniMax M2.5", "provider_id": "minimax", "provider_name": "MiniMax", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 1000000, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "model_id": "minimax/MiniMax-M2.5-lightning", "model_name": "MiniMax M2.5 Lightning", "provider_id": "minimax", "provider_name": "MiniMax", "input_cost_per_million": 0.3, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 128000, "input_cost_per_token_above_512k_tokens": 6e-7, "output_cost_per_token_above_512k_tokens": 0.0000024, "cache_read_input_token_cost_above_512k_tokens": 1.2e-7, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "model_id": "minimax/MiniMax-M3", "model_name": "MiniMax M3", "provider_id": "minimax", "provider_name": "MiniMax", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.mistral.ai/models/zai-glm-5-2", "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "glm-5-2", "model_name": "Glm 5 2", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005, "max_input_tokens": 40000, "max_output_tokens": 40000, "deprecation_date": "2026-07-31", "max_tokens": 40000, "source": "https://mistral.ai/news/magistral", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "magistral-medium-1-2-2509", "model_name": "Magistral Medium 1 2 (Sep 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 2, "output_cost_per_million": 5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005, "max_input_tokens": 40000, "max_output_tokens": 40000, "deprecation_date": "2025-11-30", "max_tokens": 40000, "source": "https://mistral.ai/news/magistral", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "magistral-medium-2506", "model_name": "Magistral Medium (Jun 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 2, "output_cost_per_million": 5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005, "max_input_tokens": 40000, "max_output_tokens": 40000, "deprecation_date": "2026-07-31", "max_tokens": 40000, "source": "https://mistral.ai/news/magistral", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "magistral-medium-2509", "model_name": "Magistral Medium (Sep 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 2, "output_cost_per_million": 5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "magistral-medium-latest", "model_name": "Magistral Medium Latest", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 40000, "max_output_tokens": 40000, "deprecation_date": "2026-07-31", "max_tokens": 40000, "source": "https://mistral.ai/pricing#api-pricing", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "magistral-small-1-2-2509", "model_name": "Magistral Small 1 2 (Sep 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.5, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 40000, "max_output_tokens": 40000, "deprecation_date": "2025-11-30", "max_tokens": 40000, "source": "https://mistral.ai/pricing#api-pricing", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "magistral-small-2506", "model_name": "Magistral Small (Jun 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.5, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "magistral-small-latest", "model_name": "Magistral Small Latest", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 1.5e-8, "cache_read_cost_per_million": 0.015, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "mistral-medium", "model_name": "Mistral Medium", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "mistral-medium-2604", "model_name": "Mistral Medium (Apr 2026)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "mistral-medium-3-5", "model_name": "Mistral Medium 3 5", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "mistral-medium-3.5", "model_name": "Mistral Medium 3.5", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "mistral-medium-latest", "model_name": "Mistral Medium 3", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "mistral-small-2603", "model_name": "Mistral Small (Mar 2026)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 1.5e-8, "cache_read_cost_per_million": 0.015, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "mistral-small-latest", "model_name": "Mistral Small", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 1.5e-8, "cache_read_cost_per_million": 0.015, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "mistral-vibe-cli-fast", "model_name": "Mistral Vibe Cli Fast", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 1.5e-8, "cache_read_cost_per_million": 0.015, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "mistral-vibe-cli-latest", "model_name": "Mistral Vibe Cli Latest", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "supports_assistant_prefill": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "mistral-vibe-cli-with-tools", "model_name": "Mistral Vibe Cli With Tools", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.mistral.ai/models/zai-glm-5-2", "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "zai-glm-5-2", "model_name": "Zai Glm 5 2", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 262144, "max_output_tokens": 262144, "deprecation_date": "2026-05-25", "max_tokens": 262144, "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "moonshot/kimi-k2-thinking", "model_name": "Kimi K2 Thinking", "provider_id": "moonshot", "provider_name": "Moonshot AI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000115, "output_cost_per_token": 0.000008, "max_input_tokens": 262144, "max_output_tokens": 262144, "deprecation_date": "2026-05-25", "max_tokens": 262144, "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "moonshot/kimi-k2-thinking-turbo", "model_name": "Kimi K2 Thinking Turbo", "provider_id": "moonshot", "provider_name": "Moonshot AI", "input_cost_per_million": 1.15, "output_cost_per_million": 8, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "model_id": "moonshot/kimi-k2.5", "model_name": "Kimi K2.5", "provider_id": "moonshot", "provider_name": "Moonshot AI", "input_cost_per_million": 0.6, "output_cost_per_million": 3, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://platform.kimi.ai/docs/pricing/chat-k26", "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "model_id": "moonshot/kimi-k2.6", "model_name": "Kimi K2.6", "provider_id": "moonshot", "provider_name": "Moonshot AI", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.6e-7, "cache_read_cost_per_million": 0.16, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://platform.kimi.ai/docs/pricing/chat-k27-code", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "model_id": "moonshot/kimi-k2.7-code", "model_name": "Kimi K2.7 Code", "provider_id": "moonshot", "provider_name": "Moonshot AI", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.9e-7, "cache_read_cost_per_million": 0.19, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "reasoning_effort_levels": [ "low", "high", "max" ], "source": "https://platform.kimi.ai/docs/pricing/chat-k3", "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "model_id": "moonshot/kimi-k3", "model_name": "Kimi K3", "provider_id": "moonshot", "provider_name": "Moonshot AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "source": "https://nebius.com/prices", "model_id": "nebius/deepseek-ai/DeepSeek-R1", "model_name": "DeepSeek R1", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 164000, "max_output_tokens": 164000, "max_tokens": 164000, "supports_reasoning": true, "source": "https://nebius.com/prices", "model_id": "nebius/deepseek-ai/DeepSeek-R1-0528", "model_name": "DeepSeek R1 0528", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash", "model_id": "nebius/deepseek-ai/DeepSeek-V4-Flash", "model_name": "DeepSeek V4 Flash", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.14, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 1024000, "max_output_tokens": 1024000, "max_tokens": 1024000, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Flash-0731", "model_id": "nebius/deepseek-ai/DeepSeek-V4-Flash-0731", "model_name": "DeepSeek V4 Flash 0731", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.14, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.0000035, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro", "model_id": "nebius/deepseek-ai/DeepSeek-V4-Pro", "model_name": "DeepSeek V4 Pro", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 1.75, "output_cost_per_million": 3.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 196608, "max_output_tokens": 196608, "max_tokens": 196608, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M2.5", "model_id": "nebius/MiniMaxAI/MiniMax-M2.5", "model_name": "MiniMax M2.5", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/MiniMaxAI%2FMiniMax-M3", "model_id": "nebius/MiniMaxAI/MiniMax-M3", "model_name": "MiniMax M3", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K2.6", "model_id": "nebius/moonshotai/Kimi-K2.6", "model_name": "Kimi K2.6", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/moonshotai%2FKimi-K2.7-Code", "model_id": "nebius/moonshotai/Kimi-K2.7-Code", "model_name": "Kimi K2.7 Code", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1024000, "max_output_tokens": 1024000, "max_tokens": 1024000, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/image2text/moonshotai%2FKimi-K3", "model_id": "nebius/moonshotai/Kimi-K3", "model_name": "Kimi K3", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-405B", "model_id": "nebius/NousResearch/Hermes-4-405B", "model_name": "Hermes 4 405B", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 1, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/NousResearch%2FHermes-4-70B", "model_id": "nebius/NousResearch/Hermes-4-70B", "model_name": "Hermes 4 70B", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.13, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/image2text/nvidia%2FCosmos3-Super-Reasoner", "model_id": "nebius/nvidia/Cosmos3-Super-Reasoner", "model_name": "Cosmos3 Super Reasoner", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000018, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FLlama-3_1-Nemotron-Ultra-253B-v1", "model_id": "nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1", "model_name": "Llama 3_1 Nemotron Ultra 253B V1", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.6, "output_cost_per_million": 1.7999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-8, "output_cost_per_token": 2.4e-7, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3_5-Lightning", "model_id": "nebius/nvidia/Nemotron-3_5-Lightning", "model_name": "Nemotron 3_5 Lightning", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.06, "output_cost_per_million": 0.24, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 6e-8, "output_cost_per_token": 2.4e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Nano-Omni", "model_id": "nebius/nvidia/Nemotron-3-Nano-Omni", "model_name": "Nemotron 3 Nano Omni", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.06, "output_cost_per_million": 0.24, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2Fnemotron-3-super-120b-a12b", "model_id": "nebius/nvidia/nemotron-3-super-120b-a12b", "model_name": "Nemotron 3 Super 120B A12B", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.3, "output_cost_per_million": 0.8999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNemotron-3-Ultra-550b-a55b", "model_id": "nebius/nvidia/Nemotron-3-Ultra-550b-a55b", "model_name": "Nemotron 3 Ultra 550B A55B", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 1, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-8, "output_cost_per_token": 2.4e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FNVIDIA-Nemotron-3-Nano-30B-A3B", "model_id": "nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B", "model_name": "NVIDIA Nemotron 3 Nano 30B A3B", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.06, "output_cost_per_million": 0.24, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/openai%2Fgpt-oss-120b", "model_id": "nebius/openai/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3-Next-80B-A3B-Thinking", "model_id": "nebius/Qwen/Qwen3-Next-80B-A3B-Thinking", "model_name": "Qwen3 Next 80B A3B Thinking", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.15, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000036, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/Qwen%2FQwen3.5-397B-A17B", "model_id": "nebius/Qwen/Qwen3.5-397B-A17B", "model_name": "Qwen3.5 397B A17B", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.6, "output_cost_per_million": 3.5999999999999996, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 4.5e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_reasoning": true, "source": "https://nebius.com/prices", "model_id": "nebius/Qwen/QwQ-32B", "model_name": "QwQ 32B", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.15, "output_cost_per_million": 0.44999999999999996, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 202752, "max_output_tokens": 202752, "max_tokens": 202752, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.1", "model_id": "nebius/zai-org/GLM-5.1", "model_name": "GLM 5.1", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.2", "model_id": "nebius/zai-org/GLM-5.2", "model_name": "GLM 5.2", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 1024000, "max_output_tokens": 1024000, "max_tokens": 1024000, "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3-Flash", "model_id": "nebius/zai-org/GLM-5.3-Flash", "model_name": "GLM 5.3 Flash", "provider_id": "nebius", "provider_name": "Nebius", "input_cost_per_million": 0.15, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 2.8e-7, "output_cost_per_token": 0.00000113, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/baidu/cobuddy", "model_name": "Cobuddy", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.28, "output_cost_per_million": 1.13, "cache_read_cost_per_token": 7e-8, "cache_read_cost_per_million": 0.07, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 7e-8, "output_cost_per_token": 2.8e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/baidu/ernie-4.5-21B-a3b-thinking", "model_name": "Ernie 4.5 21B A3B Thinking", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.07, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 5.6e-7, "max_input_tokens": 30000, "max_output_tokens": 8000, "max_tokens": 8000, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/baidu/ernie-4.5-vl-28b-a3b", "model_name": "Ernie 4.5 Vl 28B A3B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.14, "output_cost_per_million": 0.56, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3.9e-7, "output_cost_per_token": 3.9e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/baidu/ernie-4.5-vl-28b-a3b-thinking", "model_name": "Ernie 4.5 Vl 28B A3B Thinking", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.39, "output_cost_per_million": 0.39, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_vision": true, "input_cost_per_token": 4.2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 123000, "max_output_tokens": 16000, "max_tokens": 16000, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/baidu/ernie-4.5-vl-424b-a47b", "model_name": "Ernie 4.5 Vl 424B A47B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.42, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000004, "max_input_tokens": 64000, "max_output_tokens": 16000, "max_tokens": 16000, "source": "https://api.novita.ai/v3/openai/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/deepseek/deepseek-r1", "model_name": "DeepSeek R1", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 4, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_system_messages": true, "input_cost_per_token_cache_hit": 3.5e-7, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-r1-0528", "model_name": "Deepseek R1 0528", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.7, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3.5e-7, "cache_read_cost_per_million": 0.35, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "input_cost_per_token": 6e-8, "output_cost_per_token": 9e-8, "max_input_tokens": 128000, "max_output_tokens": 32000, "max_tokens": 32000, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-r1-0528-qwen3-8b", "model_name": "Deepseek R1 0528 Qwen3 8B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.06, "output_cost_per_million": 0.09, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_response_schema": true, "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-r1-distill-llama-70b", "model_name": "Deepseek R1 Distill Llama 70B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 0.7999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_function_calling": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7, "max_input_tokens": 32768, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-r1-distill-qwen-14b", "model_name": "Deepseek R1 Distill Qwen 14B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.15, "output_cost_per_million": 0.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_function_calling": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 64000, "max_output_tokens": 32000, "max_tokens": 32000, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-r1-distill-qwen-32b", "model_name": "Deepseek R1 Distill Qwen 32B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.3, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_function_calling": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 64000, "max_output_tokens": 16000, "max_tokens": 16000, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-r1-turbo", "model_name": "Deepseek R1 Turbo", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.7, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000004, "max_input_tokens": 64000, "max_output_tokens": 8000, "max_tokens": 8000, "source": "https://api.novita.ai/v3/openai/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/deepseek/deepseek-r1/community", "model_name": "Community", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 4, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_system_messages": true, "input_cost_per_token_cache_hit": 1.35e-7, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-v3.1", "model_name": "Deepseek V3.1", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.27, "output_cost_per_million": 1, "cache_read_cost_per_token": 1.35e-7, "cache_read_cost_per_million": 0.135, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_system_messages": true, "input_cost_per_token_cache_hit": 1.35e-7, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-v3.1-terminus", "model_name": "Deepseek V3.1 Terminus", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.27, "output_cost_per_million": 1, "cache_read_cost_per_token": 1.35e-7, "cache_read_cost_per_million": 0.135, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2.69e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 163840, "max_output_tokens": 65536, "max_tokens": 65536, "supports_tool_choice": true, "supports_system_messages": true, "input_cost_per_token_cache_hit": 1.345e-7, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-v3.2", "model_name": "Deepseek V3.2", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.26899999999999996, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1.345e-7, "cache_read_cost_per_million": 0.13449999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 4.1e-7, "max_input_tokens": 163840, "max_output_tokens": 65536, "max_tokens": 65536, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-v3.2-exp", "model_name": "Deepseek V3.2 Exp", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.27, "output_cost_per_million": 0.41, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/deepseek/deepseek-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.14, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 4.4e-7, "output_cost_per_token": 0.00000132, "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/deepseek/deepseek-v4-flash-0731", "model_name": "Deepseek V4 Flash 0731", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.44, "output_cost_per_million": 1.32, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4.4e-7, "output_cost_per_token": 0.00000132, "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://api.novita.ai/v3/openai/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/deepseek/deepseek-v4-flash-vision-exp", "model_name": "Deepseek V4 Flash Vision Exp", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.44, "output_cost_per_million": 1.32, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000016000000000000001, "output_cost_per_token": 0.0000032000000000000003, "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/deepseek/deepseek-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 1.6, "output_cost_per_million": 3.2, "cache_read_cost_per_token": 1.35e-7, "cache_read_cost_per_million": 0.135, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.00000132, "output_cost_per_token": 0.00000396, "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/deepseek/deepseek-v4-pro-0813", "model_name": "Deepseek V4 Pro 0813", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 1.32, "output_cost_per_million": 3.9600000000000004, "cache_read_cost_per_token": 1.3200000000000002e-7, "cache_read_cost_per_million": 0.132, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 4.0000000000000003e-7, "max_input_tokens": 262144, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://novita.ai/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/google/gemma-4-26b-a4b-it", "model_name": "Gemma 4 26B A4B It", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.13, "output_cost_per_million": 0.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 4.0000000000000003e-7, "max_input_tokens": 262144, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://novita.ai/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/google/gemma-4-31b-it", "model_name": "Gemma 4 31B It", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.14, "output_cost_per_million": 0.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 6e-8, "output_cost_per_token": 1.8e-7, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/inclusionai/ling-3.0-flash", "model_name": "Ling 3.0 Flash", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.06, "output_cost_per_million": 0.18, "cache_read_cost_per_token": 1.2e-8, "cache_read_cost_per_million": 0.012, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 6e-8, "output_cost_per_token": 1.8e-7, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/inclusionai/ling-3.0-flash-fast", "model_name": "Ling 3.0 Flash Fast", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.06, "output_cost_per_million": 0.18, "cache_read_cost_per_token": 1.2e-8, "cache_read_cost_per_million": 0.012, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 4.5000000000000003e-7, "output_cost_per_token": 0.0000026, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/mindai/macaron-v1-tall", "model_name": "Macaron V1 Tall", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.45, "output_cost_per_million": 2.6, "cache_read_cost_per_token": 8e-8, "cache_read_cost_per_million": 0.08, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000045, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/mindai/macaron-v1-venti", "model_name": "Macaron V1 Venti", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 1.5, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_system_messages": true, "input_cost_per_token_cache_hit": 3e-8, "supports_reasoning": true, "model_id": "novita/minimax/minimax-m2", "model_name": "Minimax M2", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 204800, "max_output_tokens": 131100, "max_tokens": 131100, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/minimax/minimax-m2.5", "model_name": "Minimax M2.5", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 204800, "max_output_tokens": 131100, "max_tokens": 131100, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/minimax/minimax-m2.5-highspeed", "model_name": "Minimax M2.5 Highspeed", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/minimax/minimax-m2.7", "model_name": "Minimax M2.7", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://api.novita.ai/v3/openai/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/minimax/minimax-m2.7-highspeed", "model_name": "Minimax M2.7 Highspeed", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/minimax/minimax-m3", "model_name": "Minimax M3", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 1000000, "max_output_tokens": 40000, "max_tokens": 40000, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/minimaxai/minimax-m1-80k", "model_name": "Minimax M1 80k", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.55, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 262144, "max_output_tokens": 100352, "max_tokens": 100352, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "novita/moonshotai/kimi-k2-thinking", "model_name": "Kimi K2 Thinking", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.6, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/moonshotai/kimi-k2.5", "model_name": "Kimi K2.5", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.6, "output_cost_per_million": 3, "cache_read_cost_per_token": 1.0000000000000001e-7, "cache_read_cost_per_million": 0.1, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 8.000000000000001e-7, "output_cost_per_token": 0.0000034, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/moonshotai/kimi-k2.6", "model_name": "Kimi K2.6", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.8, "output_cost_per_million": 3.4, "cache_read_cost_per_token": 1.6e-7, "cache_read_cost_per_million": 0.16, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.499999999999999e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/moonshotai/kimi-k2.7-code", "model_name": "Kimi K2.7 Code", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.9e-7, "cache_read_cost_per_million": 0.19, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/moonshotai/kimi-k3", "model_name": "Kimi K3", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 5.0000000000000004e-8, "output_cost_per_token": 2.0000000000000002e-7, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://novita.ai/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/nvidia/nemotron-3-nano-30b-a3b", "model_name": "Nemotron 3 Nano 30B A3B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.05, "output_cost_per_million": 0.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2.5e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/openai/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.25, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 4e-8, "output_cost_per_token": 1.5e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/openai/gpt-oss-20b", "model_name": "GPT Oss 20B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.04, "output_cost_per_million": 0.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_function_calling": false, "supports_parallel_functions": false }, { "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 40960, "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/qwen/qwen3-235b-a22b-fp8", "model_name": "Qwen3 235B A22B Fp8", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.7999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_function_calling": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/qwen/qwen3-235b-a22b-thinking-2507", "model_name": "Qwen3 235B A22B Thinking (Jul 2025)", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.3, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "input_cost_per_token": 9e-8, "output_cost_per_token": 4.5e-7, "max_input_tokens": 40960, "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/qwen/qwen3-30b-a3b-fp8", "model_name": "Qwen3 30B A3B Fp8", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.09, "output_cost_per_million": 0.44999999999999996, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 4.5e-7, "max_input_tokens": 40960, "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/qwen/qwen3-32b-fp8", "model_name": "Qwen3 32B Fp8", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.44999999999999996, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-8, "output_cost_per_token": 3e-8, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/qwen/qwen3-4b-fp8", "model_name": "Qwen3 4B Fp8", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.03, "output_cost_per_million": 0.03, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3.5e-8, "output_cost_per_token": 1.38e-7, "max_input_tokens": 128000, "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/qwen/qwen3-8b-fp8", "model_name": "Qwen3 8B Fp8", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.035, "output_cost_per_million": 0.13799999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/qwen/qwen3-next-80b-a3b-instruct", "model_name": "Qwen3 Next 80B A3B Instruct", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.15, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/qwen/qwen3-next-80b-a3b-thinking", "model_name": "Qwen3 Next 80B A3B Thinking", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.15, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 9.7e-7, "max_input_tokens": 65536, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "supports_audio_input": true, "model_id": "novita/qwen/qwen3-omni-30b-a3b-thinking", "model_name": "Qwen3 Omni 30B A3B Thinking", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.25, "output_cost_per_million": 0.9700000000000001, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 9.8e-7, "output_cost_per_token": 0.00000395, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_system_messages": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/qwen/qwen3-vl-235b-a22b-thinking", "model_name": "Qwen3 Vl 235B A22B Thinking", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.98, "output_cost_per_million": 3.95, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4.0000000000000003e-7, "output_cost_per_token": 0.0000032000000000000003, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://novita.ai/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/qwen/qwen3.5-122b-a10b", "model_name": "Qwen3.5 122B A10B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.4, "output_cost_per_million": 3.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://novita.ai/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/qwen/qwen3.5-27b", "model_name": "Qwen3.5 27B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.3, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://novita.ai/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/qwen/qwen3.5-35b-a3b", "model_name": "Qwen3.5 35B A3B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000036000000000000003, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://novita.ai/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/qwen/qwen3.5-397b-a17b", "model_name": "Qwen3.5 397B A17B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.6, "output_cost_per_million": 3.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000036000000000000003, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://novita.ai/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/qwen/qwen3.6-27b", "model_name": "Qwen3.6 27B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.6, "output_cost_per_million": 3.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.48e-7, "output_cost_per_token": 0.0000014850000000000002, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://novita.ai/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/qwen/qwen3.6-35b-a3b", "model_name": "Qwen3.6 35B A3B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.248, "output_cost_per_million": 1.485, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00000375, "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/qwen/qwen3.7-max", "model_name": "Qwen3.7 Max", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 1.25, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/qwen/qwen3.8-max", "model_name": "Qwen3.8 Max", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.0000000000000002e-7, "output_cost_per_token": 0.00000115, "max_input_tokens": 262144, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/stepfun/step-3.7-flash", "model_name": "Step 3.7 Flash", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.2, "output_cost_per_million": 1.15, "cache_read_cost_per_token": 4e-8, "cache_read_cost_per_million": 0.04, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 5.8e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/tencent/hy3", "model_name": "Hy3", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.14, "output_cost_per_million": 0.58, "cache_read_cost_per_token": 3.5e-8, "cache_read_cost_per_million": 0.035, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.1e-7, "output_cost_per_token": 3.3e-7, "max_input_tokens": 262144, "max_output_tokens": 32000, "max_tokens": 32000, "supports_tool_choice": true, "supports_system_messages": true, "input_cost_per_token_cache_hit": 2.4e-8, "supports_reasoning": true, "model_id": "novita/xiaomimimo/mimo-v2-flash", "model_name": "Mimo V2 Flash", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.11, "output_cost_per_million": 0.33, "cache_read_cost_per_token": 2.4e-8, "cache_read_cost_per_million": 0.024, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.6800000000000002e-7, "output_cost_per_token": 3.3600000000000004e-7, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/xiaomimimo/mimo-v2.5", "model_name": "Mimo V2.5", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.168, "output_cost_per_million": 0.336, "cache_read_cost_per_token": 3.4e-9, "cache_read_cost_per_million": 0.0034, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 5.22e-7, "output_cost_per_token": 0.000001044, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/xiaomimimo/mimo-v2.5-pro", "model_name": "Mimo V2.5 Pro", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.522, "output_cost_per_million": 1.044, "cache_read_cost_per_token": 4.3e-9, "cache_read_cost_per_million": 0.0043, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 131072, "max_output_tokens": 98304, "max_tokens": 98304, "supports_tool_choice": true, "supports_system_messages": true, "input_cost_per_token_cache_hit": 1.1e-7, "supports_reasoning": true, "model_id": "novita/zai-org/glm-4.5", "model_name": "Glm 4.5", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.6, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 8.5e-7, "max_input_tokens": 131072, "max_output_tokens": 98304, "max_tokens": 98304, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "novita/zai-org/glm-4.5-air", "model_name": "Glm 4.5 Air", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.13, "output_cost_per_million": 0.85, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000018, "max_input_tokens": 65536, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "supports_system_messages": true, "input_cost_per_token_cache_hit": 1.1e-7, "supports_reasoning": true, "model_id": "novita/zai-org/glm-4.5v", "model_name": "Glm 4.5v", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.6, "output_cost_per_million": 1.7999999999999998, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_system_messages": true, "input_cost_per_token_cache_hit": 1.1e-7, "supports_reasoning": true, "model_id": "novita/zai-org/glm-4.6", "model_name": "Glm 4.6", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.55, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_system_messages": true, "input_cost_per_token_cache_hit": 5.5e-8, "supports_reasoning": true, "model_id": "novita/zai-org/glm-4.6v", "model_name": "Glm 4.6v", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.3, "output_cost_per_million": 0.8999999999999999, "cache_read_cost_per_token": 5.5e-8, "cache_read_cost_per_million": 0.055, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_system_messages": true, "input_cost_per_token_cache_hit": 1.1e-7, "supports_reasoning": true, "model_id": "novita/zai-org/glm-4.7", "model_name": "Glm 4.7", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.6, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 7e-8, "output_cost_per_token": 4.0000000000000003e-7, "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/zai-org/glm-4.7-flash", "model_name": "Glm 4.7 Flash", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.07, "output_cost_per_million": 0.4, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://api.novita.ai/v3/openai/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/zai-org/glm-4.7-h", "model_name": "Glm 4.7 H", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.6, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032000000000000003, "max_input_tokens": 202800, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/zai-org/glm-5", "model_name": "Glm 5", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 1, "output_cost_per_million": 3.2, "cache_read_cost_per_token": 2.0000000000000002e-7, "cache_read_cost_per_million": 0.2, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000004, "max_input_tokens": 202800, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://api.novita.ai/v3/openai/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/zai-org/glm-5-turbo", "model_name": "Glm 5 Turbo", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 1.2, "output_cost_per_million": 4, "cache_read_cost_per_token": 2.4e-7, "cache_read_cost_per_million": 0.24, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.0000044, "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/zai-org/glm-5.1", "model_name": "Glm 5.1", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 1.38, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://novita.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/zai-org/glm-5.2", "model_name": "Glm 5.2", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://api.novita.ai/v3/openai/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/zai-org/glm-5.3", "model_name": "Glm 5.3", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000004, "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://api.novita.ai/v3/openai/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "novita/zai-org/glm-5v-turbo", "model_name": "Glm 5v Turbo", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 1.2, "output_cost_per_million": 4, "cache_read_cost_per_token": 2.4e-7, "cache_read_cost_per_million": 0.24, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "supports_reasoning": true, "model_id": "oci/openai.gpt-5", "model_name": "Openai.GPT-5", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "supports_reasoning": true, "model_id": "oci/openai.gpt-5-mini", "model_name": "Openai.GPT-5 Mini", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "supports_reasoning": true, "model_id": "oci/openai.gpt-5-nano", "model_name": "Openai.GPT-5 Nano", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "reasoning_effort_levels": [ "medium" ], "source": "https://developers.openai.com/api/docs/models/chat-latest", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "chat-latest", "model_name": "Chat Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000006, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-02-12", "max_tokens": 100000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "codex-mini-latest", "model_name": "Codex Mini Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.5, "output_cost_per_million": 6, "cache_read_cost_per_token": 3.75e-7, "cache_read_cost_per_million": 0.375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000012, "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://platform.openai.com/docs/models/computer-use-preview", "model_id": "computer-use-preview", "model_name": "Computer Use Preview", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 3, "output_cost_per_million": 12, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00001, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "input_cost_per_token_above_272k_tokens": 0.000008, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00003, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", "model_id": "daybreak-blue-latest", "model_name": "Daybreak Blue Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000125, "output_cost_per_token": 0.000075, "max_input_tokens": 400000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00003125, "cache_read_input_token_cost_above_272k_tokens": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000025, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", "supports_computer_use": true, "model_id": "daybreak-red-latest", "model_name": "Daybreak Red Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 12.5, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0.000015625, "cache_write_cost_per_million": 15.625, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_response_schema": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-10-23", "input_cost_per_token_batches": 0.000002, "max_tokens": 100000, "output_cost_per_token_batches": 0.000008, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "ft:o4-mini-2025-04-16", "model_name": "o4 mini (Apr 2025) [Fine-tuned]", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 16, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_flex": 6.25e-8, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_flex": 6.25e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_flex": 0.000005, "output_cost_per_token_priority": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5", "model_name": "GPT-5", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-12-11", "cache_read_input_token_cost_flex": 6.25e-8, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_flex": 6.25e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_flex": 0.000005, "output_cost_per_token_priority": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-2025-08-07", "model_name": "GPT-5 (Aug 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-chat", "model_name": "GPT-5 Chat", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-07-23", "max_tokens": 16384, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-chat-latest", "model_name": "GPT-5 Chat Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-07-23", "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-codex", "model_name": "GPT-5 Codex", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 128000, "output_cost_per_token_flex": 0.000001, "output_cost_per_token_priority": 0.0000036, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-mini", "model_name": "GPT-5 Mini", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-12-11", "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 128000, "output_cost_per_token_flex": 0.000001, "output_cost_per_token_priority": 0.0000036, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-mini-2025-08-07", "model_name": "GPT-5 Mini (Aug 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_flex": 2.5e-9, "input_cost_per_token_flex": 2.5e-8, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_flex": 2e-7, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-nano", "model_name": "GPT-5 Nano", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 5e-9, "cache_read_cost_per_million": 0.005, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-12-11", "cache_read_input_token_cost_flex": 2.5e-9, "input_cost_per_token_priority": 0.0000025, "input_cost_per_token_flex": 2.5e-8, "max_tokens": 128000, "output_cost_per_token_flex": 2e-7, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-nano-2025-08-07", "model_name": "GPT-5 Nano (Aug 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 5e-9, "cache_read_cost_per_million": 0.005, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00012, "max_input_tokens": 400000, "max_output_tokens": 272000, "input_cost_per_token_batches": 0.0000075, "max_tokens": 272000, "output_cost_per_token_batches": 0.00006, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-pro", "model_name": "GPT-5 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 15, "output_cost_per_million": 120, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00012, "max_input_tokens": 400000, "max_output_tokens": 272000, "deprecation_date": "2026-12-11", "input_cost_per_token_batches": 0.0000075, "max_tokens": 272000, "output_cost_per_token_batches": 0.00006, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-pro-2025-10-06", "model_name": "GPT-5 Pro (Oct 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 15, "output_cost_per_million": 120, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_priority": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.1", "model_name": "GPT-5.1", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_priority": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.1-2025-11-13", "model_name": "GPT-5.1 (Nov 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-07-23", "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 16384, "output_cost_per_token_priority": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.1-chat-latest", "model_name": "GPT-5.1 Chat Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-07-23", "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_priority": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-07-23", "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.1-codex-max", "model_name": "GPT-5.1 Codex Max", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-07-23", "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 128000, "output_cost_per_token_priority": 0.0000036, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 128000, "output_cost_per_token_priority": 0.000028, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.2", "model_name": "GPT-5.2", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 128000, "output_cost_per_token_priority": 0.000028, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.2-2025-12-11", "model_name": "GPT-5.2 (Dec 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-08-10", "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 16384, "output_cost_per_token_priority": 0.000028, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.2-chat-latest", "model_name": "GPT-5.2 Chat Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-07-23", "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 128000, "output_cost_per_token_priority": 0.000028, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.2-codex", "model_name": "GPT-5.2 Codex", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.2-pro", "model_name": "GPT-5.2 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 21, "output_cost_per_million": 168, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.2-pro-2025-12-11", "model_name": "GPT-5.2 Pro (Dec 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 21, "output_cost_per_million": 168, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-08-10", "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 16384, "output_cost_per_token_priority": 0.000028, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.3-chat-latest", "model_name": "GPT-5.3 Chat Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 128000, "output_cost_per_token_priority": 0.000028, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.3-codex", "model_name": "GPT-5.3 Codex", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_flex": 1.3e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_flex": 0.00000125, "input_cost_per_token_batches": 0.00000125, "input_cost_per_token_priority": 0.000005, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_flex": 0.0000075, "output_cost_per_token_batches": 0.0000075, "output_cost_per_token_priority": 0.00003, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 0.0000025, "output_cost_per_token_above_272k_tokens_flex": 0.00001125, "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-7, "model_id": "gpt-5.4", "model_name": "GPT-5.4", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 15, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_flex": 1.3e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_flex": 0.00000125, "input_cost_per_token_batches": 0.00000125, "input_cost_per_token_priority": 0.000005, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_flex": 0.0000075, "output_cost_per_token_batches": 0.0000075, "output_cost_per_token_priority": 0.00003, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 0.0000025, "output_cost_per_token_above_272k_tokens_flex": 0.00001125, "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-7, "model_id": "gpt-5.4-2026-03-05", "model_name": "GPT-5.4 (Mar 2026)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 15, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_priority": 0.0000015, "max_tokens": 128000, "output_cost_per_token_flex": 0.00000225, "output_cost_per_token_batches": 0.00000225, "output_cost_per_token_priority": 0.000009, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.4-mini", "model_name": "GPT-5.4 Mini", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_priority": 0.0000015, "max_tokens": 128000, "output_cost_per_token_flex": 0.00000225, "output_cost_per_token_batches": 0.00000225, "output_cost_per_token_priority": 0.000009, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.4-mini-2026-03-17", "model_name": "GPT-5.4 Mini (Mar 2026)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_flex": 1e-8, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_batches": 1e-7, "max_tokens": 128000, "output_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 6.25e-7, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.4-nano", "model_name": "GPT-5.4 Nano", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_flex": 1e-8, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_batches": 1e-7, "max_tokens": 128000, "output_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 6.25e-7, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.4-nano-2026-03-17", "model_name": "GPT-5.4 Nano (Mar 2026)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 0.00003, "output_cost_per_token_above_272k_tokens_flex": 0.000135, "model_id": "gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 0.00003, "output_cost_per_token_above_272k_tokens_flex": 0.000135, "model_id": "gpt-5.4-pro-2026-03-05", "model_name": "GPT-5.4 Pro (Mar 2026)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 0.00000125, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_flex": 0.0000025, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_priority": 0.0000125, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_flex": 0.000015, "output_cost_per_token_batches": 0.000015, "output_cost_per_token_priority": 0.000075, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 0.000005, "output_cost_per_token_above_272k_tokens_flex": 0.0000225, "cache_read_input_token_cost_above_272k_tokens_flex": 5e-7, "model_id": "gpt-5.5", "model_name": "GPT-5.5", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 0.00000125, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_flex": 0.0000025, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_priority": 0.0000125, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_flex": 0.000015, "output_cost_per_token_batches": 0.000015, "output_cost_per_token_priority": 0.000075, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 0.000005, "output_cost_per_token_above_272k_tokens_flex": 0.0000225, "cache_read_input_token_cost_above_272k_tokens_flex": 5e-7, "model_id": "gpt-5.5-2026-04-23", "model_name": "GPT-5.5 (Apr 2026)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false, "model_id": "gpt-5.5-pro", "model_name": "GPT-5.5 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false, "model_id": "gpt-5.5-pro-2026-04-23", "model_name": "GPT-5.5 Pro (Apr 2026)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00001, "cache_creation_input_token_cost_above_272k_tokens_flex": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00002, "cache_creation_input_token_cost_flex": 0.0000025, "cache_creation_input_token_cost_priority": 0.00001, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000016, "cache_read_input_token_cost_flex": 2e-7, "cache_read_input_token_cost_priority": 8e-7, "input_cost_per_token_above_272k_tokens": 0.000008, "input_cost_per_token_above_272k_tokens_flex": 0.000004, "input_cost_per_token_above_272k_tokens_priority": 0.000016, "input_cost_per_token_batches": 0.000002, "input_cost_per_token_flex": 0.000002, "input_cost_per_token_priority": 0.000008, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00003, "output_cost_per_token_above_272k_tokens_flex": 0.000015, "output_cost_per_token_above_272k_tokens_priority": 0.00006, "output_cost_per_token_batches": 0.00001, "output_cost_per_token_flex": 0.00001, "output_cost_per_token_priority": 0.00004, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-5.6", "model_name": "GPT-5.6", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000125, "output_cost_per_token": 0.000075, "max_input_tokens": 400000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00003125, "cache_read_input_token_cost_above_272k_tokens": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000025, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-5.6-cyber", "supports_computer_use": true, "model_id": "gpt-5.6-cyber", "model_name": "GPT-5.6 Cyber", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 12.5, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0.000015625, "cache_write_cost_per_million": 15.625, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 5e-7, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-7, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000001, "cache_creation_input_token_cost_flex": 1.25e-7, "cache_creation_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, "cache_read_input_token_cost_flex": 1e-8, "cache_read_input_token_cost_priority": 4e-8, "input_cost_per_token_above_272k_tokens": 4e-7, "input_cost_per_token_above_272k_tokens_flex": 2e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, "input_cost_per_token_batches": 1e-7, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_priority": 4e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000018, "output_cost_per_token_above_272k_tokens_flex": 9e-7, "output_cost_per_token_above_272k_tokens_priority": 0.0000036, "output_cost_per_token_batches": 6e-7, "output_cost_per_token_flex": 6e-7, "output_cost_per_token_priority": 0.0000024, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 2.5e-7, "cache_write_cost_per_million": 0.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00001, "cache_creation_input_token_cost_above_272k_tokens_flex": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00002, "cache_creation_input_token_cost_flex": 0.0000025, "cache_creation_input_token_cost_priority": 0.00001, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000016, "cache_read_input_token_cost_flex": 2e-7, "cache_read_input_token_cost_priority": 8e-7, "input_cost_per_token_above_272k_tokens": 0.000008, "input_cost_per_token_above_272k_tokens_flex": 0.000004, "input_cost_per_token_above_272k_tokens_priority": 0.000016, "input_cost_per_token_batches": 0.000002, "input_cost_per_token_flex": 0.000002, "input_cost_per_token_priority": 0.000008, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00003, "output_cost_per_token_above_272k_tokens_flex": 0.000015, "output_cost_per_token_above_272k_tokens_priority": 0.00006, "output_cost_per_token_batches": 0.00001, "output_cost_per_token_flex": 0.00001, "output_cost_per_token_priority": 0.00004, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-5.6-sol", "model_name": "GPT-5.6 Sol", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_flex": 0.0000025, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00001, "cache_creation_input_token_cost_flex": 0.00000125, "cache_creation_input_token_cost_priority": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-7, "cache_read_input_token_cost_flex": 1e-7, "cache_read_input_token_cost_priority": 4e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "input_cost_per_token_above_272k_tokens_flex": 0.000002, "input_cost_per_token_above_272k_tokens_priority": 0.000008, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000018, "output_cost_per_token_above_272k_tokens_flex": 0.000009, "output_cost_per_token_above_272k_tokens_priority": 0.000036, "output_cost_per_token_batches": 0.000006, "output_cost_per_token_flex": 0.000006, "output_cost_per_token_priority": 0.000024, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-5.6-terra", "model_name": "GPT-5.6 Terra", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000025, "cache_creation_input_token_cost_above_272k_tokens_flex": 0.0000125, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00005, "cache_creation_input_token_cost_flex": 0.00000625, "cache_creation_input_token_cost_priority": 0.000025, "cache_read_input_token_cost_above_272k_tokens": 0.000002, "cache_read_input_token_cost_above_272k_tokens_flex": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000004, "cache_read_input_token_cost_flex": 5e-7, "cache_read_input_token_cost_priority": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00002, "input_cost_per_token_above_272k_tokens_flex": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00004, "input_cost_per_token_batches": 0.000005, "input_cost_per_token_flex": 0.000005, "input_cost_per_token_priority": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000075, "output_cost_per_token_above_272k_tokens_flex": 0.0000375, "output_cost_per_token_above_272k_tokens_priority": 0.00015, "output_cost_per_token_batches": 0.000025, "output_cost_per_token_flex": 0.000025, "output_cost_per_token_priority": 0.0001, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-6-astra", "model_name": "GPT-6 Astra", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00001, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "input_cost_per_token_above_272k_tokens": 0.000008, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00003, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", "model_id": "gpt-daybreak-blue-latest", "model_name": "GPT Daybreak Blue Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 5, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000125, "output_cost_per_token": 0.000075, "max_input_tokens": 400000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00003125, "cache_read_input_token_cost_above_272k_tokens": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000025, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", "supports_computer_use": true, "model_id": "gpt-daybreak-red-latest", "model_name": "GPT Daybreak Red Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 12.5, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0.000015625, "cache_write_cost_per_million": 15.625, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-10-23", "max_tokens": 100000, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "o1", "model_name": "o1", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 15, "output_cost_per_million": 60, "cache_read_cost_per_token": 0.0000075, "cache_read_cost_per_million": 7.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-10-23", "max_tokens": 100000, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "o1-2024-12-17", "model_name": "o1 (Dec 2024)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 15, "output_cost_per_million": 60, "cache_read_cost_per_token": 0.0000075, "cache_read_cost_per_million": 7.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00015, "output_cost_per_token": 0.0006, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-10-23", "input_cost_per_token_batches": 0.000075, "max_tokens": 100000, "output_cost_per_token_batches": 0.0003, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "o1-pro", "model_name": "o1 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 150, "output_cost_per_million": 600, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00015, "output_cost_per_token": 0.0006, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-10-23", "input_cost_per_token_batches": 0.000075, "max_tokens": 100000, "output_cost_per_token_batches": 0.0003, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "o1-pro-2025-03-19", "model_name": "o1 Pro (Mar 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 150, "output_cost_per_million": 600, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 200000, "max_output_tokens": 100000, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.0000035, "max_tokens": 100000, "output_cost_per_token_flex": 0.000004, "output_cost_per_token_priority": 0.000014, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses", "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o3", "model_name": "o3", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-12-11", "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.0000035, "max_tokens": 100000, "output_cost_per_token_flex": 0.000004, "output_cost_per_token_priority": 0.000014, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses", "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o3-2025-04-16", "model_name": "o3 (Apr 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00004, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-07-23", "input_cost_per_token_batches": 0.000005, "max_tokens": 100000, "output_cost_per_token_batches": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o3-deep-research", "model_name": "O3 Deep Research", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 10, "output_cost_per_million": 40, "cache_read_cost_per_token": 0.0000025, "cache_read_cost_per_million": 2.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00004, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-07-23", "input_cost_per_token_batches": 0.000005, "max_tokens": 100000, "output_cost_per_token_batches": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o3-deep-research-2025-06-26", "model_name": "O3 Deep Research (Jun 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 10, "output_cost_per_million": 40, "cache_read_cost_per_token": 0.0000025, "cache_read_cost_per_million": 2.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-10-23", "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "o3-mini", "model_name": "o3 mini", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-10-23", "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "o3-mini-2025-01-31", "model_name": "o3 mini (Jan 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00002, "output_cost_per_token": 0.00008, "max_input_tokens": 200000, "max_output_tokens": 100000, "input_cost_per_token_batches": 0.00001, "max_tokens": 100000, "output_cost_per_token_batches": 0.00004, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o3-pro", "model_name": "o3 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 20, "output_cost_per_million": 80, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00002, "output_cost_per_token": 0.00008, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-12-11", "input_cost_per_token_batches": 0.00001, "max_tokens": 100000, "output_cost_per_token_batches": 0.00004, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o3-pro-2025-06-10", "model_name": "o3 Pro (Jun 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 20, "output_cost_per_million": 80, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-10-23", "cache_read_input_token_cost_flex": 1.375e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token_flex": 5.5e-7, "input_cost_per_token_priority": 0.000002, "max_tokens": 100000, "output_cost_per_token_flex": 0.0000022, "output_cost_per_token_priority": 0.000008, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o4-mini", "model_name": "o4 mini", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.75e-7, "cache_read_cost_per_million": 0.275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-10-23", "cache_read_input_token_cost_flex": 1.375e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token_flex": 5.5e-7, "input_cost_per_token_priority": 0.000002, "max_tokens": 100000, "output_cost_per_token_flex": 0.0000022, "output_cost_per_token_priority": 0.000008, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o4-mini-2025-04-16", "model_name": "o4 mini (Apr 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.75e-7, "cache_read_cost_per_million": 0.275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-07-23", "input_cost_per_token_batches": 0.000001, "max_tokens": 100000, "output_cost_per_token_batches": 0.000004, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o4-mini-deep-research", "model_name": "O4 Mini Deep Research", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-07-23", "input_cost_per_token_batches": 0.000001, "max_tokens": 100000, "output_cost_per_token_batches": 0.000004, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o4-mini-deep-research-2025-06-26", "model_name": "O4 Mini Deep Research (Jun 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 128000, "input_cost_per_image": 0.0048, "max_tokens": 128000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/anthropic/claude-3.7-sonnet", "model_name": "Claude 3.7 Sonnet", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_sampling_params": false, "supports_adaptive_thinking": true, "thinking_always_on": true, "source": "https://openrouter.ai/anthropic/claude-fable-5", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "prompt_cache_min_tokens": 512, "model_id": "openrouter/anthropic/claude-fable-5", "model_name": "Claude Fable 5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_sampling_params": false, "supports_adaptive_thinking": true, "thinking_always_on": true, "source": "https://openrouter.ai/anthropic/claude-fable-5.1", "supports_tool_choice": false, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "prompt_cache_min_tokens": 512, "model_id": "openrouter/anthropic/claude-fable-5.1", "model_name": "Claude Fable 5.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 4096, "source": "https://openrouter.ai/anthropic/claude-haiku-4.5", "model_id": "openrouter/anthropic/claude-haiku-4.5", "model_name": "Claude Haiku 4.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "input_cost_per_image": 0.0048, "max_tokens": 32000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "openrouter/anthropic/claude-opus-4", "model_name": "Claude Opus 4", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "input_cost_per_image": 0.0048, "cache_creation_input_token_cost_above_1hr": 0.00003, "max_tokens": 32000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "openrouter/anthropic/claude-opus-4.1", "model_name": "Claude Opus 4.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096, "source": "https://openrouter.ai/anthropic/claude-opus-4.5", "model_id": "openrouter/anthropic/claude-opus-4.5", "model_name": "Claude Opus 4.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "max_tokens": 128000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 4096, "source": "https://openrouter.ai/api/v1/models", "model_id": "openrouter/anthropic/claude-opus-4.6", "model_name": "Claude Opus 4.6", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "max_tokens": 128000, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "prompt_cache_min_tokens": 2048, "model_id": "openrouter/anthropic/claude-opus-4.7", "model_name": "Claude Opus 4.7", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_sampling_params": false, "supports_adaptive_thinking": true, "source": "https://openrouter.ai/anthropic/claude-opus-4.8", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/anthropic/claude-opus-4.8", "model_name": "Claude Opus 4.8", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "max_tokens": 128000, "source": "https://openrouter.ai/anthropic/claude-opus-5", "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "openrouter/anthropic/claude-opus-5", "model_name": "Claude Opus 5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "input_cost_per_image": 0.0048, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "openrouter/anthropic/claude-sonnet-4", "model_name": "Claude Sonnet 4", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "input_cost_per_image": 0.0048, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "source": "https://openrouter.ai/anthropic/claude-sonnet-4.5", "model_id": "openrouter/anthropic/claude-sonnet-4.5", "model_name": "Claude Sonnet 4.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_above_200k_tokens": 0.000006, "max_tokens": 128000, "output_cost_per_token_above_200k_tokens": 0.0000225, "source": "https://openrouter.ai/anthropic/claude-sonnet-4.6", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "openrouter/anthropic/claude-sonnet-4.6", "model_name": "Claude Sonnet 4.6", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_sampling_params": false, "supports_adaptive_thinking": true, "source": "https://openrouter.ai/anthropic/claude-sonnet-5", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/anthropic/claude-sonnet-5", "model_name": "Claude Sonnet 5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 9.5e-7, "max_input_tokens": 163840, "max_output_tokens": 163840, "input_cost_per_token_cache_hit": 2e-8, "max_tokens": 163840, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://openrouter.ai/deepseek/deepseek-chat-v3.1", "model_id": "openrouter/deepseek/deepseek-chat-v3.1", "model_name": "Deepseek Chat V3.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.25, "output_cost_per_million": 0.95, "cache_read_cost_per_token": 1.3e-7, "cache_read_cost_per_million": 0.13, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 65336, "max_output_tokens": 8192, "input_cost_per_token_cache_hit": 1.4e-7, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/deepseek/deepseek-r1", "model_name": "DeepSeek R1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.7, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.00000215, "max_input_tokens": 65336, "max_output_tokens": 8192, "input_cost_per_token_cache_hit": 1.4e-7, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/deepseek/deepseek-r1-0528", "model_name": "Deepseek R1 0528", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.5, "output_cost_per_million": 2.1500000000000004, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": false, "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 8192, "max_output_tokens": 7372, "max_tokens": 7372, "source": "https://openrouter.ai/deepseek/deepseek-r1-distill-llama-70b", "supports_tool_choice": false, "supports_reasoning": true, "model_id": "openrouter/deepseek/deepseek-r1-distill-llama-70b", "model_name": "Deepseek R1 Distill Llama 70B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 0.7999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/deepseek/deepseek-v3.1-terminus", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/deepseek/deepseek-v3.1-terminus", "model_name": "Deepseek V3.1 Terminus", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.27, "output_cost_per_million": 1, "cache_read_cost_per_token": 1.35e-7, "cache_read_cost_per_million": 0.135, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2.69e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 163840, "max_output_tokens": 65536, "input_cost_per_token_cache_hit": 1.345e-7, "max_tokens": 65536, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://openrouter.ai/api/v1/models", "model_id": "openrouter/deepseek/deepseek-v3.2", "model_name": "Deepseek V3.2", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.26899999999999996, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 8.54e-8, "output_cost_per_token": 1.708e-7, "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "source": "https://openrouter.ai/deepseek/deepseek-v4-flash", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/deepseek/deepseek-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.0854, "output_cost_per_million": 0.1708, "cache_read_cost_per_token": 1.708e-8, "cache_read_cost_per_million": 0.01708, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 6.5e-8, "output_cost_per_token": 1.8e-7, "max_input_tokens": 1310720, "max_output_tokens": 943718, "max_tokens": 943718, "source": "https://openrouter.ai/deepseek/deepseek-v4-flash-0731", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/deepseek/deepseek-v4-flash-0731", "model_name": "Deepseek V4 Flash 0731", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.065, "output_cost_per_million": 0.18, "cache_read_cost_per_token": 1.6e-8, "cache_read_cost_per_million": 0.016, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 6.6e-7, "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "source": "https://openrouter.ai/deepseek/deepseek-v4-flash-vision-exp", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/deepseek/deepseek-v4-flash-vision-exp", "model_name": "Deepseek V4 Flash Vision Exp", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.22, "output_cost_per_million": 0.66, "cache_read_cost_per_token": 7e-9, "cache_read_cost_per_million": 0.007, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 8.59908e-7, "output_cost_per_token": 0.000001719816, "max_input_tokens": 1048576, "max_output_tokens": 384000, "input_cost_per_token_cache_hit": 4.4e-8, "max_tokens": 384000, "source": "https://openrouter.ai/deepseek/deepseek-v4-pro", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/deepseek/deepseek-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.859908, "output_cost_per_million": 1.719816, "cache_read_cost_per_token": 7.1659e-8, "cache_read_cost_per_million": 0.071659, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 5.7948e-7, "output_cost_per_token": 0.00000173844, "max_input_tokens": 1048576, "max_output_tokens": 384000, "input_cost_per_token_cache_hit": 4.4e-8, "max_tokens": 384000, "source": "https://openrouter.ai/deepseek/deepseek-v4-pro-0813", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/deepseek/deepseek-v4-pro-0813", "model_name": "Deepseek V4 Pro 0813", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.57948, "output_cost_per_million": 1.73844, "cache_read_cost_per_token": 1.9316e-8, "cache_read_cost_per_million": 0.019316, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "source": "https://openrouter.ai/deepseek/deepseek-v4.1-flash", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": false, "supports_prompt_caching": true, "model_id": "openrouter/deepseek/deepseek-v4.1-flash", "model_name": "Deepseek V4.1 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 3e-9, "cache_read_cost_per_million": 0.003, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_tokens": 65535, "source": "https://openrouter.ai/google/gemini-2.5-flash-lite", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "supports_prompt_caching": true, "model_id": "openrouter/google/gemini-2.5-flash-lite", "model_name": "Gemini 2.5 Flash Lite", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_audio_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000015, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "max_tokens": 65536, "source": "https://openrouter.ai/google/gemini-2.5-pro-preview", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "supports_prompt_caching": true, "model_id": "openrouter/google/gemini-2.5-pro-preview", "model_name": "Gemini 2.5 Pro Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000015, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "max_tokens": 65535, "source": "https://openrouter.ai/google/gemini-2.5-pro-preview-05-06", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "supports_prompt_caching": true, "model_id": "openrouter/google/gemini-2.5-pro-preview-05-06", "model_name": "Gemini 2.5 Pro Preview 05 06", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.000003, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 800000, "model_id": "openrouter/google/gemini-3-flash-preview", "model_name": "Gemini 3 Flash Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 131072, "max_output_tokens": 32768, "input_cost_per_audio_token": 0.000002, "output_cost_per_image_token": 0.00012, "max_tokens": 32768, "source": "https://openrouter.ai/google/gemini-3-pro-image", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/google/gemini-3-pro-image", "model_name": "Gemini 3 Pro Image", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 65536, "max_output_tokens": 32768, "input_cost_per_audio_token": 0.000002, "output_cost_per_image_token": 0.00012, "max_tokens": 32768, "source": "https://openrouter.ai/google/gemini-3-pro-image-preview", "supports_tool_choice": false, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/google/gemini-3-pro-image-preview", "model_name": "Gemini 3 Pro Image Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "model_id": "openrouter/google/gemini-3-pro-preview", "model_name": "Gemini 3 Pro Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 131072, "max_output_tokens": 32768, "output_cost_per_image_token": 0.00006, "max_tokens": 32768, "source": "https://openrouter.ai/google/gemini-3.1-flash-image", "supports_tool_choice": false, "supports_reasoning": true, "model_id": "openrouter/google/gemini-3.1-flash-image", "model_name": "Gemini 3.1 Flash Image", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 65536, "max_output_tokens": 58982, "output_cost_per_image_token": 0.00006, "max_tokens": 58982, "source": "https://openrouter.ai/google/gemini-3.1-flash-image-preview", "supports_tool_choice": false, "supports_reasoning": true, "model_id": "openrouter/google/gemini-3.1-flash-image-preview", "model_name": "Gemini 3.1 Flash Image Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_audio_token": 5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "tpm": 800000, "model_id": "openrouter/google/gemini-3.1-flash-lite", "model_name": "Gemini 3.1 Flash Lite", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 65536, "max_output_tokens": 58982, "output_cost_per_image_token": 0.00003, "max_tokens": 58982, "source": "https://openrouter.ai/google/gemini-3.1-flash-lite-image", "supports_tool_choice": false, "supports_reasoning": true, "model_id": "openrouter/google/gemini-3.1-flash-lite-image", "model_name": "Gemini 3.1 Flash Lite Image", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_audio_token": 5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "tpm": 800000, "model_id": "openrouter/google/gemini-3.1-flash-lite-preview", "model_name": "Gemini 3.1 Flash Lite Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "source": "https://openrouter.ai/google/gemini-3.1-pro-preview", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "openrouter/google/gemini-3.1-pro-preview", "model_name": "Gemini 3.1 Pro Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_audio_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "output_cost_per_token_above_200k_tokens": 0.000018, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "max_tokens": 65536, "source": "https://openrouter.ai/google/gemini-3.1-pro-preview-customtools", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "supports_prompt_caching": true, "model_id": "openrouter/google/gemini-3.1-pro-preview-customtools", "model_name": "Gemini 3.1 Pro Preview Customtools", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000009, "max_input_tokens": 1048576, "max_output_tokens": 65535, "max_tokens": 65535, "source": "https://openrouter.ai/google/gemini-3.5-flash", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "supports_prompt_caching": true, "model_id": "openrouter/google/gemini-3.5-flash", "model_name": "Gemini 3.5 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.5, "output_cost_per_million": 9, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/google/gemini-3.5-flash-lite", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "supports_prompt_caching": true, "model_id": "openrouter/google/gemini-3.5-flash-lite", "model_name": "Gemini 3.5 Flash Lite", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/google/gemini-3.6-flash", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "supports_prompt_caching": true, "model_id": "openrouter/google/gemini-3.6-flash", "model_name": "Gemini 3.6 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/google/gemini-3.7-flash", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "supports_prompt_caching": true, "model_id": "openrouter/google/gemini-3.7-flash", "model_name": "Gemini 3.7 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/google/gemini-3.8-flash", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "supports_prompt_caching": true, "model_id": "openrouter/google/gemini-3.8-flash", "model_name": "Gemini 3.8 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4.2e-8, "output_cost_per_token": 2.2e-7, "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://openrouter.ai/google/gemma-4-26b-a4b-it", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/google/gemma-4-26b-a4b-it", "model_name": "Gemma 4 26B A4B It", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.041999999999999996, "output_cost_per_million": 0.22, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/google/gemma-4-26b-a4b-it:free", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/google/gemma-4-26b-a4b-it:free", "model_name": "Gemma 4 26B A4B It:free", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9e-8, "output_cost_per_token": 3.4e-7, "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://openrouter.ai/google/gemma-4-31b-it", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/google/gemma-4-31b-it", "model_name": "Gemma 4 31B It", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09, "output_cost_per_million": 0.33999999999999997, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/google/gemma-4-31b-it:free", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/google/gemma-4-31b-it:free", "model_name": "Gemma 4 31B It:free", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 1000000, "max_output_tokens": 40000, "max_tokens": 40000, "source": "https://openrouter.ai/minimax/minimax-m1", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/minimax/minimax-m1", "model_name": "Minimax M1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.55, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.55e-7, "output_cost_per_token": 0.00000102, "max_input_tokens": 204800, "max_output_tokens": 204800, "max_tokens": 204800, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/minimax/minimax-m2", "model_name": "Minimax M2", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.255, "output_cost_per_million": 1.02, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 204000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": false, "supports_computer_use": false, "model_id": "openrouter/minimax/minimax-m2.1", "model_name": "Minimax M2.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.00000108, "max_input_tokens": 196608, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/minimax/minimax-m2.5", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_computer_use": false, "model_id": "openrouter/minimax/minimax-m2.5", "model_name": "Minimax M2.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.27, "output_cost_per_million": 1.08, "cache_read_cost_per_token": 2.7e-8, "cache_read_cost_per_million": 0.027, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://openrouter.ai/minimax/minimax-m2.7", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/minimax/minimax-m2.7", "model_name": "Minimax M2.7", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 196608, "max_output_tokens": 176947, "max_tokens": 176947, "source": "https://openrouter.ai/minimax/minimax-m2.7:free", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/minimax/minimax-m2.7:free", "model_name": "Minimax M2.7:free", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1048576, "max_output_tokens": 512000, "max_tokens": 512000, "source": "https://openrouter.ai/minimax/minimax-m3", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/minimax/minimax-m3", "model_name": "Minimax M3", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 1048576, "max_output_tokens": 943718, "max_tokens": 943718, "source": "https://openrouter.ai/minimax/minimax-m3:free", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/minimax/minimax-m3:free", "model_name": "Minimax M3:free", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 262144, "max_output_tokens": 209715, "max_tokens": 209715, "source": "https://openrouter.ai/mistralai/mistral-medium-3-5", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "model_id": "openrouter/mistralai/mistral-medium-3-5", "model_name": "Mistral Medium 3 5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 262144, "max_output_tokens": 209715, "max_tokens": 209715, "source": "https://openrouter.ai/mistralai/mistral-small-2603", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/mistralai/mistral-small-2603", "model_name": "Mistral Small (Mar 2026)", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 1.5e-8, "cache_read_cost_per_million": 0.015, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 262144, "max_output_tokens": 100352, "max_tokens": 100352, "source": "https://openrouter.ai/moonshotai/kimi-k2-thinking", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/moonshotai/kimi-k2-thinking", "model_name": "Kimi K2 Thinking", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.6, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 235929, "max_tokens": 235929, "source": "https://openrouter.ai/moonshotai/kimi-k2.6", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/moonshotai/kimi-k2.6", "model_name": "Kimi K2.6", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.6e-7, "cache_read_cost_per_million": 0.16, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.1e-7, "output_cost_per_token": 0.0000035, "max_input_tokens": 262144, "max_output_tokens": 235929, "max_tokens": 235929, "source": "https://openrouter.ai/moonshotai/kimi-k2.7-code", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/moonshotai/kimi-k2.7-code", "model_name": "Kimi K2.7 Code", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.71, "output_cost_per_million": 3.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000021, "output_cost_per_token": 0.00001053, "max_input_tokens": 1048576, "max_output_tokens": 943718, "max_tokens": 943718, "source": "https://openrouter.ai/moonshotai/kimi-k3", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/moonshotai/kimi-k3", "model_name": "Kimi K3", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2.0999999999999996, "output_cost_per_million": 10.530000000000001, "cache_read_cost_per_token": 2.35e-7, "cache_read_cost_per_million": 0.235, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 262144, "max_output_tokens": 235929, "max_tokens": 235929, "source": "https://openrouter.ai/nvidia/nemotron-3-nano-30b-a3b", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/nvidia/nemotron-3-nano-30b-a3b", "model_name": "Nemotron 3 Nano 30B A3B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 256000, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "supports_tool_choice": true, "supports_reasoning": true, "supports_audio_input": true, "model_id": "openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "model_name": "Nemotron 3 Nano Omni 30B A3B Reasoning:free", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 8.5e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/nvidia/nemotron-3-super-120b-a12b", "model_name": "Nemotron 3 Super 120B A12B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.08499999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 262144, "max_output_tokens": 235929, "max_tokens": 235929, "source": "https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b:free", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/nvidia/nemotron-3-super-120b-a12b:free", "model_name": "Nemotron 3 Super 120B A12B:free", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 6.25e-7, "output_cost_per_token": 0.000003125, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/nvidia/nemotron-3-ultra-550b-a55b", "model_name": "Nemotron 3 Ultra 550B A55B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.625, "output_cost_per_million": 3.125, "cache_read_cost_per_token": 1.875e-7, "cache_read_cost_per_million": 0.1875, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b:free", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/nvidia/nemotron-3-ultra-550b-a55b:free", "model_name": "Nemotron 3 Ultra 550B A55B:free", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 131072, "max_output_tokens": 117964, "max_tokens": 117964, "source": "https://openrouter.ai/nvidia/nemotron-3.5-content-safety", "supports_tool_choice": false, "supports_reasoning": true, "model_id": "openrouter/nvidia/nemotron-3.5-content-safety", "model_name": "Nemotron 3.5 Content Safety", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://openrouter.ai/nvidia/nemotron-3.5-content-safety:free", "supports_tool_choice": false, "supports_reasoning": true, "model_id": "openrouter/nvidia/nemotron-3.5-content-safety:free", "model_name": "Nemotron 3.5 Content Safety:free", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 8e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 262144, "source": "https://openrouter.ai/nvidia/nemotron-3.5-lightning", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/nvidia/nemotron-3.5-lightning", "model_name": "Nemotron 3.5 Lightning", "provider_id": "openrouter", "provider_name": "OpenRouter", "max_output_tokens": 0, "input_cost_per_million": 0.08, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/nvidia/nemotron-3.5-lightning:free", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/nvidia/nemotron-3.5-lightning:free", "model_name": "Nemotron 3.5 Lightning:free", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-5", "model_name": "GPT-5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-5-chat", "model_name": "GPT-5 Chat", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-5-codex", "model_name": "GPT-5 Codex", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-5-mini", "model_name": "GPT-5 Mini", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-5-nano", "model_name": "GPT-5 Nano", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 5e-9, "cache_read_cost_per_million": 0.005, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00012, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5-pro", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "model_id": "openrouter/openai/gpt-5-pro", "model_name": "GPT-5 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 15, "output_cost_per_million": 120, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.1", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.1-codex", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.3e-7, "cache_read_cost_per_million": 0.13, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.1-codex-max", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-5.1-codex-max", "model_name": "GPT-5.1 Codex Max", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.1-codex-mini", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "input_cost_per_image": 0, "max_tokens": 128000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-5.2", "model_name": "GPT-5.2", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-5.2-codex", "model_name": "GPT-5.2 Codex", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168, "max_input_tokens": 272000, "max_output_tokens": 128000, "input_cost_per_image": 0, "max_tokens": 128000, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-5.2-pro", "model_name": "GPT-5.2 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 21, "output_cost_per_million": 168, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.3-codex", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-5.3-codex", "model_name": "GPT-5.3 Codex", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.4", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2.5, "output_cost_per_million": 15, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.4-mini", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-5.4-mini", "model_name": "GPT-5.4 Mini", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.4-nano", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-5.4-nano", "model_name": "GPT-5.4 Nano", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00006, "output_cost_per_token_above_272k_tokens": 0.00027, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.4-pro", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "model_id": "openrouter/openai/gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.5", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00006, "output_cost_per_token_above_272k_tokens": 0.00027, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.5-pro", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "model_id": "openrouter/openai/gpt-5.5-pro", "model_name": "GPT-5.5 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.6-luna", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 4e-7, "output_cost_per_token_above_272k_tokens": 0.0000018, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.6-luna-pro", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-5.6-luna-pro", "model_name": "GPT-5.6 Luna Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 2.5e-7, "cache_write_cost_per_million": 0.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "default_reasoning_effort": "medium", "input_cost_per_token_above_272k_tokens": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "reasoning_effort_levels": [ "none", "low", "medium", "high", "xhigh", "max" ], "source": "https://openrouter.ai/openai/gpt-5.6-sol", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-5.6-sol", "model_name": "GPT-5.6 Sol", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.000004, "output_cost_per_token_above_272k_tokens": 0.000015, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.6-sol-pro", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-5.6-sol-pro", "model_name": "GPT-5.6 Sol Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.6-terra", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-5.6-terra", "model_name": "GPT-5.6 Terra", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.000004, "output_cost_per_token_above_272k_tokens": 0.000018, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-5.6-terra-pro", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-5.6-terra-pro", "model_name": "GPT-5.6 Terra Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00002, "output_cost_per_token_above_272k_tokens": 0.000075, "cache_read_input_token_cost_above_272k_tokens": 0.000002, "cache_creation_input_token_cost_above_272k_tokens": 0.000025, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-6-astra", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-6-astra", "model_name": "GPT-6 Astra", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00002, "output_cost_per_token_above_272k_tokens": 0.000075, "cache_read_input_token_cost_above_272k_tokens": 0.000002, "max_tokens": 128000, "source": "https://openrouter.ai/openai/gpt-6-astra-pro", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-6-astra-pro", "model_name": "GPT-6 Astra Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 3.7e-8, "output_cost_per_token": 1.7e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/openai/gpt-oss-120b", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.037, "output_cost_per_million": 0.16999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 3e-8, "output_cost_per_token": 1.3e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/openai/gpt-oss-20b", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-oss-20b", "model_name": "GPT Oss 20B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.03, "output_cost_per_million": 0.13, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/openai/gpt-oss-safeguard-20b", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/openai/gpt-oss-safeguard-20b", "model_name": "GPT Oss Safeguard 20B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.075, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 3.75e-8, "cache_read_cost_per_million": 0.0375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00015, "output_cost_per_token": 0.0006, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "source": "https://openrouter.ai/openai/o1-pro", "supports_tool_choice": false, "supports_reasoning": true, "supports_pdf_input": true, "model_id": "openrouter/openai/o1-pro", "model_name": "o1 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 150, "output_cost_per_million": 600, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "source": "https://openrouter.ai/openai/o3", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/openai/o3", "model_name": "o3", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_reasoning": true, "supports_tool_choice": true, "supports_prompt_caching": true, "source": "https://openrouter.ai/openai/o3-mini", "model_id": "openrouter/openai/o3-mini", "model_name": "o3 mini", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_reasoning": true, "supports_tool_choice": true, "supports_prompt_caching": true, "source": "https://openrouter.ai/openai/o3-mini-high", "model_id": "openrouter/openai/o3-mini-high", "model_name": "O3 Mini High", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00002, "output_cost_per_token": 0.00008, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "source": "https://openrouter.ai/openai/o3-pro", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "model_id": "openrouter/openai/o3-pro", "model_name": "o3 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 20, "output_cost_per_million": 80, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "source": "https://openrouter.ai/openai/o4-mini", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/openai/o4-mini", "model_name": "o4 mini", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.75e-7, "cache_read_cost_per_million": 0.275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "source": "https://openrouter.ai/openai/o4-mini-high", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": true, "model_id": "openrouter/openai/o4-mini-high", "model_name": "O4 Mini High", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.75e-7, "cache_read_cost_per_million": 0.275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 2000000, "max_tokens": 2000000, "supports_tool_choice": true, "supports_reasoning": true, "supports_audio_input": true, "supports_video_input": true, "model_id": "openrouter/openrouter/auto", "model_name": "Auto", "provider_id": "openrouter", "provider_name": "OpenRouter", "max_output_tokens": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 200000, "max_tokens": 200000, "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/openrouter/free", "model_name": "Free", "provider_id": "openrouter", "provider_name": "OpenRouter", "max_output_tokens": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 9e-8, "output_cost_per_token": 1.8e-7, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://openrouter.ai/poolside/laguna-s-2.1", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/poolside/laguna-s-2.1", "model_name": "Laguna S 2.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09, "output_cost_per_million": 0.18, "cache_read_cost_per_token": 9e-9, "cache_read_cost_per_million": 0.009, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/poolside/laguna-s-2.1:free", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/poolside/laguna-s-2.1:free", "model_name": "Laguna S 2.1:free", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 6e-8, "output_cost_per_token": 1.2e-7, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/poolside/laguna-xs-2.1", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/poolside/laguna-xs-2.1", "model_name": "Laguna Xs 2.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.06, "output_cost_per_million": 0.12, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/poolside/laguna-xs-2.1:free", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/poolside/laguna-xs-2.1:free", "model_name": "Laguna Xs 2.1:free", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 2.275e-7, "output_cost_per_token": 9.1e-7, "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://openrouter.ai/qwen/qwen3-14b", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3-14b", "model_name": "Qwen3 14B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.22749999999999998, "output_cost_per_million": 0.9099999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 4.55e-7, "output_cost_per_token": 0.00000182, "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://openrouter.ai/qwen/qwen3-235b-a22b", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3-235b-a22b", "model_name": "Qwen3 235B A22B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.45499999999999996, "output_cost_per_million": 1.8199999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.3e-7, "output_cost_per_token": 0.0000023, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/qwen/qwen3-235b-a22b-thinking-2507", "model_name": "Qwen3 235B A22B Thinking (Jul 2025)", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.22999999999999998, "output_cost_per_million": 2.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://openrouter.ai/qwen/qwen3-30b-a3b", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3-30b-a3b", "model_name": "Qwen3 30B A3B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.12, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 81920, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/qwen/qwen3-30b-a3b-thinking-2507", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3-30b-a3b-thinking-2507", "model_name": "Qwen3 30B A3B Thinking (Jul 2025)", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 8e-8, "output_cost_per_token": 2.8e-7, "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://openrouter.ai/qwen/qwen3-32b", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3-32b", "model_name": "Qwen3 32B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.08, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.17e-7, "output_cost_per_token": 4.55e-7, "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://openrouter.ai/qwen/qwen3-8b", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3-8b", "model_name": "Qwen3 8B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.117, "output_cost_per_million": 0.45499999999999996, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6.5e-7, "output_cost_per_token": 0.00000325, "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/qwen/qwen3-coder-plus", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/qwen/qwen3-coder-plus", "model_name": "Qwen3 Coder Plus", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.65, "output_cost_per_million": 3.25, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 7.8e-7, "output_cost_per_token": 0.0000039, "max_input_tokens": 262144, "max_output_tokens": 65536, "input_cost_per_token_above_128k_tokens": 0.00000195, "output_cost_per_token_above_128k_tokens": 0.00000975, "max_tokens": 65536, "source": "https://openrouter.ai/qwen/qwen3-max-thinking", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3-max-thinking", "model_name": "Qwen3 Max Thinking", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.78, "output_cost_per_million": 3.9, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/qwen/qwen3-next-80b-a3b-thinking", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3-next-80b-a3b-thinking", "model_name": "Qwen3 Next 80B A3B Thinking", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.15, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/qwen/qwen3-vl-235b-a22b-thinking", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3-vl-235b-a22b-thinking", "model_name": "Qwen3 Vl 235B A22B Thinking", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/qwen/qwen3-vl-30b-a3b-thinking", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3-vl-30b-a3b-thinking", "model_name": "Qwen3 Vl 30B A3B Thinking", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 0.0000021, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/qwen/qwen3-vl-8b-thinking", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3-vl-8b-thinking", "model_name": "Qwen3 Vl 8B Thinking", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.18, "output_cost_per_million": 2.0999999999999996, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2.6e-7, "output_cost_per_token": 0.00000208, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/qwen/qwen3.5-122b-a10b", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/qwen/qwen3.5-122b-a10b", "model_name": "Qwen3.5 122B A10B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.26, "output_cost_per_million": 2.08, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 1.95e-7, "output_cost_per_token": 0.00000156, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/qwen/qwen3.5-27b", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/qwen/qwen3.5-27b", "model_name": "Qwen3.5 27B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.195, "output_cost_per_million": 1.56, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 3.125e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/qwen/qwen3.5-35b-a3b", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/qwen/qwen3.5-35b-a3b", "model_name": "Qwen3.5 35B A3B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.3125, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 1.5625e-7, "cache_read_cost_per_million": 0.15625, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.0000035, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/qwen/qwen3.5-397b-a17b", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/qwen/qwen3.5-397b-a17b", "model_name": "Qwen3.5 397B A17B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.55, "output_cost_per_million": 3.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 1.5e-7, "max_input_tokens": 262144, "max_output_tokens": 235929, "max_tokens": 235929, "source": "https://openrouter.ai/qwen/qwen3.5-9b", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3.5-9b", "model_name": "Qwen3.5 9B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 6.5e-8, "output_cost_per_token": 2.6e-7, "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/qwen/qwen3.5-flash-02-23", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/qwen/qwen3.5-flash-02-23", "model_name": "Qwen3.5 Flash 02 23", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.065, "output_cost_per_million": 0.26, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2.6e-7, "output_cost_per_token": 0.00000156, "max_input_tokens": 1000000, "max_output_tokens": 65536, "input_cost_per_token_above_256k_tokens": 5e-7, "max_tokens": 65536, "output_cost_per_token_above_256k_tokens": 0.000003, "source": "https://openrouter.ai/qwen/qwen3.5-plus-02-15", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/qwen/qwen3.5-plus-02-15", "model_name": "Qwen3.5 Plus 02 15", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.26, "output_cost_per_million": 1.56, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000018, "max_input_tokens": 1000000, "max_output_tokens": 65536, "input_cost_per_token_above_256k_tokens": 3.75e-7, "output_cost_per_token_above_256k_tokens": 0.00000225, "cache_creation_input_token_cost_above_256k_tokens": 4.6875e-7, "max_tokens": 65536, "source": "https://openrouter.ai/qwen/qwen3.5-plus-20260420", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3.5-plus-20260420", "model_name": "Qwen3.5 Plus (Apr 2026)", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.3, "output_cost_per_million": 1.7999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/qwen/qwen3.6-27b", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/qwen/qwen3.6-27b", "model_name": "Qwen3.6 27B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.3, "output_cost_per_million": 2, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 262144, "max_output_tokens": 235929, "max_tokens": 235929, "source": "https://openrouter.ai/qwen/qwen3.6-35b-a3b", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/qwen/qwen3.6-35b-a3b", "model_name": "Qwen3.6 35B A3B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.8999999999999999, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.875e-7, "output_cost_per_token": 0.000001125, "max_input_tokens": 1000000, "max_output_tokens": 65536, "input_cost_per_token_above_256k_tokens": 7.5e-7, "output_cost_per_token_above_256k_tokens": 0.000003, "cache_creation_input_token_cost_above_256k_tokens": 9.375e-7, "max_tokens": 65536, "source": "https://openrouter.ai/qwen/qwen3.6-flash", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3.6-flash", "model_name": "Qwen3.6 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.1875, "output_cost_per_million": 1.125, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 2.34375e-7, "cache_write_cost_per_million": 0.234375, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.000001027, "output_cost_per_token": 0.000006162, "max_input_tokens": 262144, "max_output_tokens": 65536, "input_cost_per_token_above_128k_tokens": 0.00000158, "output_cost_per_token_above_128k_tokens": 0.00000948, "cache_creation_input_token_cost_above_128k_tokens": 0.000001975, "max_tokens": 65536, "source": "https://openrouter.ai/qwen/qwen3.6-max-preview", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/qwen/qwen3.6-max-preview", "model_name": "Qwen3.6 Max Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.0270000000000001, "output_cost_per_million": 6.162, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0.00000128375, "cache_write_cost_per_million": 1.28375, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 3.25e-7, "output_cost_per_token": 0.00000195, "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/qwen/qwen3.6-plus", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/qwen/qwen3.6-plus", "model_name": "Qwen3.6 Plus", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.325, "output_cost_per_million": 1.95, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-8, "output_cost_per_token": 1.3e-7, "max_input_tokens": 1000000, "max_output_tokens": 65536, "input_cost_per_token_above_256k_tokens": 2e-7, "output_cost_per_token_above_256k_tokens": 8e-7, "cache_read_input_token_cost_above_256k_tokens": 4e-8, "cache_creation_input_token_cost_above_256k_tokens": 2.5e-7, "max_tokens": 65536, "source": "https://openrouter.ai/qwen/qwen3.7-flash", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/qwen/qwen3.7-flash", "model_name": "Qwen3.7 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.03, "output_cost_per_million": 0.13, "cache_read_cost_per_token": 6e-9, "cache_read_cost_per_million": 0.006, "cache_write_cost_per_token": 3.8e-8, "cache_write_cost_per_million": 0.038000000000000006, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.000001475, "output_cost_per_token": 0.000004425, "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://openrouter.ai/qwen/qwen3.7-max", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/qwen/qwen3.7-max", "model_name": "Qwen3.7 Max", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.475, "output_cost_per_million": 4.425, "cache_read_cost_per_token": 2.95e-7, "cache_read_cost_per_million": 0.295, "cache_write_cost_per_token": 0.00000184375, "cache_write_cost_per_million": 1.84375, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3.2e-7, "output_cost_per_token": 0.00000128, "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://openrouter.ai/qwen/qwen3.7-plus", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/qwen/qwen3.7-plus", "model_name": "Qwen3.7 Plus", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.32, "output_cost_per_million": 1.28, "cache_read_cost_per_token": 6.4e-8, "cache_read_cost_per_million": 0.064, "cache_write_cost_per_token": 4e-7, "cache_write_cost_per_million": 0.39999999999999997, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 1048576, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://openrouter.ai/qwen/qwen3.8-2.4t-a95b", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/qwen/qwen3.8-2.4t-a95b", "model_name": "Qwen3.8 2.4t A95B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4.2e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://openrouter.ai/qwen/qwen3.8-27b", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/qwen/qwen3.8-27b", "model_name": "Qwen3.8 27B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.42, "output_cost_per_million": 3, "cache_read_cost_per_token": 8.5e-8, "cache_read_cost_per_million": 0.08499999999999999, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 4.7e-7, "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://openrouter.ai/qwen/qwen3.8-flash", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/qwen/qwen3.8-flash", "model_name": "Qwen3.8 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.15, "output_cost_per_million": 0.47, "cache_read_cost_per_token": 1.6e-8, "cache_read_cost_per_million": 0.016, "cache_write_cost_per_token": 2e-7, "cache_write_cost_per_million": 0.19999999999999998, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://openrouter.ai/qwen/qwen3.8-max", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/qwen/qwen3.8-max", "model_name": "Qwen3.8 Max", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://openrouter.ai/qwen/qwen3.8-max-0902", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": false, "supports_prompt_caching": true, "model_id": "openrouter/qwen/qwen3.8-max-0902", "model_name": "Qwen3.8 Max (Feb 2009)", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://openrouter.ai/x-ai/grok-4", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/x-ai/grok-4", "model_name": "Grok 4", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://openrouter.ai/x-ai/grok-4.20", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/x-ai/grok-4.20", "model_name": "Grok 4.20", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://openrouter.ai/x-ai/grok-4.20-multi-agent", "supports_tool_choice": false, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/x-ai/grok-4.20-multi-agent", "model_name": "Grok 4.20 Multi Agent", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://openrouter.ai/x-ai/grok-4.3", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/x-ai/grok-4.3", "model_name": "Grok 4.3", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 500000, "max_tokens": 500000, "source": "https://openrouter.ai/x-ai/grok-4.5", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/x-ai/grok-4.5", "model_name": "Grok 4.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 500000, "max_tokens": 500000, "source": "https://openrouter.ai/x-ai/grok-4.6", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/x-ai/grok-4.6", "model_name": "Grok 4.6", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000002, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://openrouter.ai/x-ai/grok-build-0.1", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "model_id": "openrouter/x-ai/grok-build-0.1", "model_name": "Grok Build 0.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1, "output_cost_per_million": 2, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/xiaomi/mimo-v2-flash", "model_name": "Mimo V2 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_reasoning": true, "supports_audio_input": true, "supports_video_input": true, "supports_prompt_caching": true, "model_id": "openrouter/xiaomi/mimo-v2.5", "model_name": "Mimo V2.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.14, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 2.8e-9, "cache_read_cost_per_million": 0.0028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 4.35e-7, "output_cost_per_token": 8.7e-7, "max_input_tokens": 1048576, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/xiaomi/mimo-v2.5-pro", "model_name": "Mimo V2.5 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.435, "output_cost_per_million": 0.87, "cache_read_cost_per_token": 3.6e-9, "cache_read_cost_per_million": 0.0036, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 131072, "max_output_tokens": 98304, "max_tokens": 98304, "source": "https://openrouter.ai/z-ai/glm-4.5", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/z-ai/glm-4.5", "model_name": "Glm 4.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.6, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 8.5e-7, "max_input_tokens": 131072, "max_output_tokens": 98304, "max_tokens": 98304, "source": "https://openrouter.ai/z-ai/glm-4.5-air", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/z-ai/glm-4.5-air", "model_name": "Glm 4.5 Air", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.13, "output_cost_per_million": 0.85, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000018, "max_input_tokens": 65536, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://openrouter.ai/z-ai/glm-4.5v", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/z-ai/glm-4.5v", "model_name": "Glm 4.5v", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.6, "output_cost_per_million": 1.7999999999999998, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4.3e-7, "output_cost_per_token": 0.00000175, "max_input_tokens": 202800, "max_output_tokens": 131000, "max_tokens": 131000, "source": "https://openrouter.ai/z-ai/glm-4.6", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/z-ai/glm-4.6", "model_name": "Glm 4.6", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.43, "output_cost_per_million": 1.75, "cache_read_cost_per_token": 8e-8, "cache_read_cost_per_million": 0.08, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4.5e-7, "output_cost_per_token": 0.0000019, "max_input_tokens": 202800, "max_output_tokens": 131000, "max_tokens": 131000, "source": "https://openrouter.ai/z-ai/glm-4.6:exacto", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/z-ai/glm-4.6:exacto", "model_name": "Glm 4.6:exacto", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.44999999999999996, "output_cost_per_million": 1.9, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/z-ai/glm-4.6v", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/z-ai/glm-4.6v", "model_name": "Glm 4.6v", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.3, "output_cost_per_million": 0.8999999999999999, "cache_read_cost_per_token": 5.5e-8, "cache_read_cost_per_million": 0.055, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.00000175, "max_input_tokens": 202752, "max_output_tokens": 64000, "max_tokens": 64000, "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": false, "supports_assistant_prefill": true, "model_id": "openrouter/z-ai/glm-4.7", "model_name": "Glm 4.7", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.75, "cache_read_cost_per_token": 8e-8, "cache_read_cost_per_million": 0.08, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 6e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": false, "model_id": "openrouter/z-ai/glm-4.7-flash", "model_name": "Glm 4.7 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.06, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.00000192, "max_input_tokens": 202752, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/z-ai/glm-5", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/z-ai/glm-5", "model_name": "Glm 5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.6, "output_cost_per_million": 1.92, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000004, "max_input_tokens": 202752, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://openrouter.ai/z-ai/glm-5-turbo", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/z-ai/glm-5-turbo", "model_name": "Glm 5 Turbo", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.2, "output_cost_per_million": 4, "cache_read_cost_per_token": 2.4e-7, "cache_read_cost_per_million": 0.24, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 9.66e-7, "output_cost_per_token": 0.000003036, "max_input_tokens": 202752, "max_output_tokens": 65535, "max_tokens": 65535, "source": "https://openrouter.ai/z-ai/glm-5.1", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openrouter/z-ai/glm-5.1", "model_name": "Glm 5.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.966, "output_cost_per_million": 3.036, "cache_read_cost_per_token": 1.794e-7, "cache_read_cost_per_million": 0.1794, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://openrouter.ai/z-ai/glm-5.2", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/z-ai/glm-5.2", "model_name": "Glm 5.2", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.6, "output_cost_per_million": 2, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 256000, "max_output_tokens": 230400, "max_tokens": 230400, "source": "https://openrouter.ai/z-ai/glm-5.2:free", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "openrouter/z-ai/glm-5.2:free", "model_name": "Glm 5.2:free", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1310720, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://openrouter.ai/z-ai/glm-5.3", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/z-ai/glm-5.3", "model_name": "Glm 5.3", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 1310720, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://openrouter.ai/z-ai/glm-5.3-flash", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/z-ai/glm-5.3-flash", "model_name": "Glm 5.3 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.15, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000004, "max_input_tokens": 202752, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://openrouter.ai/z-ai/glm-5v-turbo", "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "model_id": "openrouter/z-ai/glm-5v-turbo", "model_name": "Glm 5v Turbo", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.2, "output_cost_per_million": 4, "cache_read_cost_per_token": 2.4e-7, "cache_read_cost_per_million": 0.24, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 6.7e-7, "output_cost_per_token": 6.7e-7, "max_input_tokens": 131000, "max_output_tokens": 131000, "max_tokens": 131000, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "ovhcloud/DeepSeek-R1-Distill-Llama-70B", "model_name": "DeepSeek R1 Distill Llama 70B", "provider_id": "ovhcloud", "provider_name": "Ovhcloud", "input_cost_per_million": 0.67, "output_cost_per_million": 0.67, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_response_schema": true, "input_cost_per_token": 8e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 131000, "max_output_tokens": 131000, "max_tokens": 131000, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_reasoning": true, "supports_tool_choice": false, "model_id": "ovhcloud/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "ovhcloud", "provider_name": "Ovhcloud", "input_cost_per_million": 0.08, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_response_schema": true, "input_cost_per_token": 4e-8, "output_cost_per_token": 1.5e-7, "max_input_tokens": 131000, "max_output_tokens": 131000, "max_tokens": 131000, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_reasoning": true, "supports_tool_choice": false, "model_id": "ovhcloud/gpt-oss-20b", "model_name": "GPT Oss 20B", "provider_id": "ovhcloud", "provider_name": "Ovhcloud", "input_cost_per_million": 0.04, "output_cost_per_million": 0.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 8e-8, "output_cost_per_token": 2.3e-7, "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "source": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "ovhcloud/Qwen3-32B", "model_name": "Qwen3 32B", "provider_id": "ovhcloud", "provider_name": "Ovhcloud", "input_cost_per_million": 0.08, "output_cost_per_million": 0.22999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "supports_web_search": true, "supports_reasoning": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.2", "model_name": "GPT-5.2", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 2.6e-7, "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": true, "model_id": "perplexity/deepseek-v4-flash-0731", "model_name": "Deepseek V4 Flash 0731", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.13, "output_cost_per_million": 0.26, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": true, "model_id": "perplexity/glm-5.2", "model_name": "Glm 5.2", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "reasoning_effort_levels": [ "minimal", "low", "medium", "high", "xhigh", "max" ], "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": true, "model_id": "perplexity/kimi-k3", "model_name": "Kimi K3", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000025, "supports_web_search": true, "supports_reasoning": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "perplexity/nemotron-3-ultra-550b-a55b", "model_name": "Nemotron 3 Ultra 550B A55B", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.15e-8, "output_cost_per_token": 1.7e-7, "supports_web_search": true, "supports_reasoning": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "perplexity/nemotron-3.5-lightning-30b-a3b", "model_name": "Nemotron 3.5 Lightning 30B A3B", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.0115, "output_cost_per_million": 0.16999999999999998, "cache_read_cost_per_token": 1.15e-9, "cache_read_cost_per_million": 0.00115, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 128000, "citation_cost_per_token": 0.000002, "max_tokens": 128000, "output_cost_per_reasoning_token": 0.000003, "search_context_cost_per_query": { "search_context_size_high": 0.005, "search_context_size_low": 0.005, "search_context_size_medium": 0.005 }, "supports_reasoning": true, "supports_web_search": true, "model_id": "sonar-deep-research", "model_name": "Sonar Deep Research", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 128000, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.005, "search_context_size_medium": 0.008 }, "supports_reasoning": true, "supports_web_search": true, "model_id": "sonar-reasoning", "model_name": "Sonar Reasoning", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_output_tokens": 0, "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 128000, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.006, "search_context_size_medium": 0.01 }, "supports_reasoning": true, "supports_web_search": true, "model_id": "sonar-reasoning-pro", "model_name": "Sonar Reasoning Pro", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_assistant_prefill": true, "supports_reasoning": true, "source": "https://pinstripes.io/", "model_id": "pinstripes/ps/deepseek-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "pinstripes", "provider_name": "Pinstripes", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.25e-7, "output_cost_per_token": 4.5e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_assistant_prefill": true, "supports_reasoning": true, "source": "https://pinstripes.io/", "model_id": "pinstripes/ps/glm-4.5-air", "model_name": "Glm 4.5 Air", "provider_id": "pinstripes", "provider_name": "Pinstripes", "input_cost_per_million": 0.125, "output_cost_per_million": 0.44999999999999996, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 9e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_assistant_prefill": true, "supports_reasoning": true, "source": "https://pinstripes.io/", "model_id": "pinstripes/ps/qwen3-30b-a3b", "model_name": "Qwen3 30B A3B", "provider_id": "pinstripes", "provider_name": "Pinstripes", "input_cost_per_million": 0.09, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 4.5e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_assistant_prefill": true, "supports_reasoning": true, "source": "https://pinstripes.io/", "model_id": "pinstripes/ps/qwen3.6-35b-a3b", "model_name": "Qwen3.6 35B A3B", "provider_id": "pinstripes", "provider_name": "Pinstripes", "input_cost_per_million": 0.14, "output_cost_per_million": 0.44999999999999996, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://platform.publicai.co/docs", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "publicai/allenai/Olmo-3-32B-Think", "model_name": "Olmo 3 32B Think", "provider_id": "publicai", "provider_name": "Publicai", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://platform.publicai.co/docs", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "publicai/allenai/Olmo-3-7B-Think", "model_name": "Olmo 3 7B Think", "provider_id": "publicai", "provider_name": "Publicai", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/deepseek-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 4e-8, "cache_read_cost_per_million": 0.04, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/deepseek-v4-flash-0731", "model_name": "Deepseek V4 Flash 0731", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 4e-8, "cache_read_cost_per_million": 0.04, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.0000048, "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/deepseek-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 2.4, "output_cost_per_million": 4.8, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 202745, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/glm-5.1", "model_name": "Glm 5.1", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/glm-5.2", "model_name": "Glm 5.2", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 229376, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/kimi-k2.7-code", "model_name": "Kimi K2.7 Code", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.9e-7, "cache_read_cost_per_million": 0.19, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen-coder", "model_name": "Qwen Coder", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.3, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "range": [ 0, 256000 ] }, { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "range": [ 256000, 1000000 ] } ], "model_id": "qwen_ai_platform/qwen-flash", "model_name": "Qwen Flash", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "range": [ 0, 256000 ] }, { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "range": [ 256000, 1000000 ] } ], "model_id": "qwen_ai_platform/qwen-flash-2025-07-28", "model_name": "Qwen Flash (Jul 2025)", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000016, "output_cost_per_token": 0.0000064, "max_input_tokens": 30720, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen-max", "model_name": "Qwen Max", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 1.5999999999999999, "output_cost_per_million": 6.3999999999999995, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen-plus", "model_name": "Qwen Plus", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 129024, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen-plus-2025-01-25", "model_name": "Qwen Plus (Jan 2025)", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 0.000004, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen-plus-2025-04-28", "model_name": "Qwen Plus (Apr 2025)", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 0.000004, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen-plus-2025-07-14", "model_name": "Qwen Plus (Jul 2025)", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012, "range": [ 0, 256000 ] }, { "input_cost_per_token": 0.0000012, "output_cost_per_reasoning_token": 0.000012, "output_cost_per_token": 0.0000036, "range": [ 256000, 1000000 ] } ], "model_id": "qwen_ai_platform/qwen-plus-2025-07-28", "model_name": "Qwen Plus (Jul 2025)", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012, "range": [ 0, 256000 ] }, { "input_cost_per_token": 0.0000012, "output_cost_per_reasoning_token": 0.000012, "output_cost_per_token": 0.0000036, "range": [ 256000, 1000000 ] } ], "model_id": "qwen_ai_platform/qwen-plus-2025-09-11", "model_name": "Qwen Plus (Sep 2025)", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012, "range": [ 0, 256000 ] }, { "input_cost_per_token": 0.0000012, "output_cost_per_reasoning_token": 0.000012, "output_cost_per_token": 0.0000036, "range": [ 256000, 1000000 ] } ], "model_id": "qwen_ai_platform/qwen-plus-latest", "model_name": "Qwen Plus Latest", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 5e-7, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen-turbo", "model_name": "Qwen Turbo", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen-turbo-2024-11-01", "model_name": "Qwen Turbo (Nov 2024)", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 5e-7, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen-turbo-2025-04-28", "model_name": "Qwen Turbo (Apr 2025)", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 5e-7, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen-turbo-latest", "model_name": "Qwen Turbo Latest", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen3-30b-a3b", "model_name": "Qwen3 30B A3B", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015, "range": [ 0, 32000 ] }, { "cache_read_input_token_cost": 1.2e-7, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000025, "range": [ 32000, 128000 ] }, { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004, "range": [ 128000, 256000 ] }, { "cache_read_input_token_cost": 4e-7, "input_cost_per_token": 0.0000016, "output_cost_per_token": 0.0000096, "range": [ 256000, 1000000 ] } ], "model_id": "qwen_ai_platform/qwen3-coder-flash", "model_name": "Qwen3 Coder Flash", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015, "range": [ 0, 32000 ] }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000025, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004, "range": [ 128000, 256000 ] }, { "input_cost_per_token": 0.0000016, "output_cost_per_token": 0.0000096, "range": [ 256000, 1000000 ] } ], "model_id": "qwen_ai_platform/qwen3-coder-flash-2025-07-28", "model_name": "Qwen3 Coder Flash (Jul 2025)", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "range": [ 0, 32000 ] }, { "cache_read_input_token_cost": 1.8e-7, "input_cost_per_token": 0.0000018, "output_cost_per_token": 0.000009, "range": [ 32000, 128000 ] }, { "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 256000 ] }, { "cache_read_input_token_cost": 6e-7, "input_cost_per_token": 0.000006, "output_cost_per_token": 0.00006, "range": [ 256000, 1000000 ] } ], "model_id": "qwen_ai_platform/qwen3-coder-plus", "model_name": "Qwen3 Coder Plus", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000018, "output_cost_per_token": 0.000009, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 256000 ] }, { "input_cost_per_token": 0.000006, "output_cost_per_token": 0.00006, "range": [ 256000, 1000000 ] } ], "model_id": "qwen_ai_platform/qwen3-coder-plus-2025-07-22", "model_name": "Qwen3 Coder Plus (Jul 2025)", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 258048, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 252000 ] } ], "model_id": "qwen_ai_platform/qwen3-max", "model_name": "Qwen3 Max", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 258048, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 252000 ] } ], "model_id": "qwen_ai_platform/qwen3-max-2026-01-23", "model_name": "Qwen3 Max (Jan 2026)", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 258048, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 252000 ] } ], "model_id": "qwen_ai_platform/qwen3-max-preview", "model_name": "Qwen3 Max Preview", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen3-next-80b-a3b-thinking", "model_name": "Qwen3 Next 80B A3B Thinking", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.15, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen3-vl-235b-a22b-thinking", "model_name": "Qwen3 Vl 235B A22B Thinking", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 1.6e-7, "output_cost_per_token": 0.00000287, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen3-vl-32b-thinking", "model_name": "Qwen3 Vl 32B Thinking", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.16, "output_cost_per_million": 2.87, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "max_input_tokens": 260096, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000016, "range": [ 0, 32000 ] }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000024, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000048, "range": [ 128000, 256000 ] } ], "model_id": "qwen_ai_platform/qwen3-vl-plus", "model_name": "Qwen3 Vl Plus", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000024, "range": [ 0, 256000 ] }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "range": [ 256000, 1000000 ] } ], "model_id": "qwen_ai_platform/qwen3.5-plus", "model_name": "Qwen3.5 Plus", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.0000075, "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen3.7-max", "model_name": "Qwen3.7 Max", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 2.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "range": [ 0, 256000 ] }, { "cache_read_input_token_cost": 2.4e-7, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000048, "range": [ 256000, 1000000 ] } ], "model_id": "qwen_ai_platform/qwen3.7-plus", "model_name": "Qwen3.7 Plus", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 991808, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwen3.8-max", "model_name": "Qwen3.8 Max", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 98304, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.alibabacloud.com/help/en/model-studio/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwen_ai_platform/qwq-plus", "model_name": "Qwq Plus", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://www.qwencloud.com/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/deepseek-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 4e-8, "cache_read_cost_per_million": 0.04, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://www.qwencloud.com/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/deepseek-v4-flash-0731", "model_name": "Deepseek V4 Flash 0731", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 4e-8, "cache_read_cost_per_million": 0.04, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.0000048, "max_input_tokens": 1000000, "max_output_tokens": 393216, "max_tokens": 393216, "source": "https://www.qwencloud.com/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/deepseek-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 2.4, "output_cost_per_million": 4.8, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 202745, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://www.qwencloud.com/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/glm-5.1", "model_name": "Glm 5.1", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://www.qwencloud.com/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/glm-5.2", "model_name": "Glm 5.2", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 229376, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://www.qwencloud.com/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/kimi-k2.7-code", "model_name": "Kimi K2.7 Code", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.9e-7, "cache_read_cost_per_million": 0.19, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen-coder", "model_name": "Qwen Coder", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.3, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "range": [ 0, 256000 ] }, { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "range": [ 256000, 1000000 ] } ], "model_id": "qwencloud/qwen-flash", "model_name": "Qwen Flash", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "range": [ 0, 256000 ] }, { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "range": [ 256000, 1000000 ] } ], "model_id": "qwencloud/qwen-flash-2025-07-28", "model_name": "Qwen Flash (Jul 2025)", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000016, "output_cost_per_token": 0.0000064, "max_input_tokens": 30720, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen-max", "model_name": "Qwen Max", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 1.5999999999999999, "output_cost_per_million": 6.3999999999999995, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen-plus", "model_name": "Qwen Plus", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 129024, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen-plus-2025-01-25", "model_name": "Qwen Plus (Jan 2025)", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 0.000004, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen-plus-2025-04-28", "model_name": "Qwen Plus (Apr 2025)", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 0.000004, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen-plus-2025-07-14", "model_name": "Qwen Plus (Jul 2025)", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012, "range": [ 0, 256000 ] }, { "input_cost_per_token": 0.0000012, "output_cost_per_reasoning_token": 0.000012, "output_cost_per_token": 0.0000036, "range": [ 256000, 1000000 ] } ], "model_id": "qwencloud/qwen-plus-2025-07-28", "model_name": "Qwen Plus (Jul 2025)", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012, "range": [ 0, 256000 ] }, { "input_cost_per_token": 0.0000012, "output_cost_per_reasoning_token": 0.000012, "output_cost_per_token": 0.0000036, "range": [ 256000, 1000000 ] } ], "model_id": "qwencloud/qwen-plus-2025-09-11", "model_name": "Qwen Plus (Sep 2025)", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_reasoning_token": 0.000004, "output_cost_per_token": 0.0000012, "range": [ 0, 256000 ] }, { "input_cost_per_token": 0.0000012, "output_cost_per_reasoning_token": 0.000012, "output_cost_per_token": 0.0000036, "range": [ 256000, 1000000 ] } ], "model_id": "qwencloud/qwen-plus-latest", "model_name": "Qwen Plus Latest", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 5e-7, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen-turbo", "model_name": "Qwen Turbo", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen-turbo-2024-11-01", "model_name": "Qwen Turbo (Nov 2024)", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 5e-7, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen-turbo-2025-04-28", "model_name": "Qwen Turbo (Apr 2025)", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "output_cost_per_reasoning_token": 5e-7, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen-turbo-latest", "model_name": "Qwen Turbo Latest", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 129024, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen3-30b-a3b", "model_name": "Qwen3 30B A3B", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015, "range": [ 0, 32000 ] }, { "cache_read_input_token_cost": 1.2e-7, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000025, "range": [ 32000, 128000 ] }, { "cache_read_input_token_cost": 2e-7, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004, "range": [ 128000, 256000 ] }, { "cache_read_input_token_cost": 4e-7, "input_cost_per_token": 0.0000016, "output_cost_per_token": 0.0000096, "range": [ 256000, 1000000 ] } ], "model_id": "qwencloud/qwen3-coder-flash", "model_name": "Qwen3 Coder Flash", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000015, "range": [ 0, 32000 ] }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000025, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004, "range": [ 128000, 256000 ] }, { "input_cost_per_token": 0.0000016, "output_cost_per_token": 0.0000096, "range": [ 256000, 1000000 ] } ], "model_id": "qwencloud/qwen3-coder-flash-2025-07-28", "model_name": "Qwen3 Coder Flash (Jul 2025)", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 1e-7, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "range": [ 0, 32000 ] }, { "cache_read_input_token_cost": 1.8e-7, "input_cost_per_token": 0.0000018, "output_cost_per_token": 0.000009, "range": [ 32000, 128000 ] }, { "cache_read_input_token_cost": 3e-7, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 256000 ] }, { "cache_read_input_token_cost": 6e-7, "input_cost_per_token": 0.000006, "output_cost_per_token": 0.00006, "range": [ 256000, 1000000 ] } ], "model_id": "qwencloud/qwen3-coder-plus", "model_name": "Qwen3 Coder Plus", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 997952, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000018, "output_cost_per_token": 0.000009, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 256000 ] }, { "input_cost_per_token": 0.000006, "output_cost_per_token": 0.00006, "range": [ 256000, 1000000 ] } ], "model_id": "qwencloud/qwen3-coder-plus-2025-07-22", "model_name": "Qwen3 Coder Plus (Jul 2025)", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 258048, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 252000 ] } ], "model_id": "qwencloud/qwen3-max", "model_name": "Qwen3 Max", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 258048, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 252000 ] } ], "model_id": "qwencloud/qwen3-max-2026-01-23", "model_name": "Qwen3 Max (Jan 2026)", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 258048, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000006, "range": [ 0, 32000 ] }, { "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "range": [ 128000, 252000 ] } ], "model_id": "qwencloud/qwen3-max-preview", "model_name": "Qwen3 Max Preview", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen3-next-80b-a3b-thinking", "model_name": "Qwen3 Next 80B A3B Thinking", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.15, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen3-vl-235b-a22b-thinking", "model_name": "Qwen3 Vl 235B A22B Thinking", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 1.6e-7, "output_cost_per_token": 0.00000287, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen3-vl-32b-thinking", "model_name": "Qwen3 Vl 32B Thinking", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.16, "output_cost_per_million": 2.87, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "max_input_tokens": 260096, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000016, "range": [ 0, 32000 ] }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000024, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000048, "range": [ 128000, 256000 ] } ], "model_id": "qwencloud/qwen3-vl-plus", "model_name": "Qwen3 Vl Plus", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000024, "range": [ 0, 256000 ] }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "range": [ 256000, 1000000 ] } ], "model_id": "qwencloud/qwen3.5-plus", "model_name": "Qwen3.5 Plus", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.0000075, "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.qwencloud.com/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen3.7-max", "model_name": "Qwen3.7 Max", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 2.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "max_input_tokens": 991808, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.qwencloud.com/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "tiered_pricing": [ { "cache_read_input_token_cost": 8e-8, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "range": [ 0, 256000 ] }, { "cache_read_input_token_cost": 2.4e-7, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000048, "range": [ 256000, 1000000 ] } ], "model_id": "qwencloud/qwen3.7-plus", "model_name": "Qwen3.7 Plus", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 991808, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://www.qwencloud.com/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwen3.8-max", "model_name": "Qwen3.8 Max", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 98304, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.qwencloud.com/models", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "qwencloud/qwq-plus", "model_name": "Qwq Plus", "provider_id": "qwencloud", "provider_name": "Qwencloud", "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000375, "output_cost_per_token": 0.00001, "max_input_tokens": 65536, "max_output_tokens": 8192, "output_cost_per_reasoning_token": 0.00001, "max_tokens": 8192, "supports_reasoning": true, "supports_system_messages": true, "model_id": "deepseek-ai/deepseek-r1", "model_name": "DeepSeek R1", "provider_id": "replicate", "provider_name": "Replicate", "input_cost_per_million": 3.75, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6.72e-7, "output_cost_per_token": 0.000002016, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_system_messages": true, "model_id": "deepseek-ai/deepseek-v3.1", "model_name": "Deepseek V3.1", "provider_id": "replicate", "provider_name": "Replicate", "input_cost_per_million": 0.6719999999999999, "output_cost_per_million": 2.016, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "output_cost_per_reasoning_token": 0.00006, "supports_reasoning": true, "supports_system_messages": true, "model_id": "openai/o1", "model_name": "o1", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 15, "output_cost_per_million": 60, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "output_cost_per_reasoning_token": 0.0000044, "supports_reasoning": true, "supports_system_messages": true, "model_id": "openai/o1-mini", "model_name": "o1 mini", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000004, "output_cost_per_reasoning_token": 0.000004, "supports_reasoning": true, "supports_system_messages": true, "model_id": "openai/o4-mini", "model_name": "o4 mini", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.0000045, "max_input_tokens": 32768, "max_output_tokens": 32768, "deprecation_date": "2026-04-14", "max_tokens": 32768, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "sambanova/DeepSeek-V3-0324", "model_name": "DeepSeek V3 0324", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 3, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.0000045, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://cloud.sambanova.ai/plans/pricing", "model_id": "sambanova/DeepSeek-V3.1", "model_name": "DeepSeek V3.1", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 3, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 5.9e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_reasoning": true, "source": "https://cloud.sambanova.ai/plans/pricing", "model_id": "sambanova/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.22, "output_cost_per_million": 0.59, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 196608, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "sambanova/MiniMax-M2.7", "model_name": "MiniMax M2.7", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "deprecation_date": "2026-04-06", "max_tokens": 8192, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "sambanova/Qwen3-32B", "model_name": "Qwen3 32B", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 0.7999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_output_tokens": 32000, "cache_creation_input_token_cost_above_1hr": 0, "max_tokens": 32000, "supports_reasoning": true, "model_id": "sarvam/sarvam-m", "model_name": "Sarvam M", "provider_id": "sarvam", "provider_name": "Sarvam", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 4e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 256000, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.scaleway.com/en/pricing/model-as-a-service/", "supports_prompt_caching": true, "supports_reasoning": true, "model_id": "scaleway/deepseek-v4-flash-0731", "model_name": "Deepseek V4 Flash 0731", "provider_id": "scaleway", "provider_name": "Scaleway", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 0.7999999999999999, "cache_read_cost_per_token": 8e-8, "cache_read_cost_per_million": 0.08, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.0000018, "output_cost_per_token": 0.0000055, "max_input_tokens": 256000, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://www.scaleway.com/en/pricing/model-as-a-service/", "supports_reasoning": true, "model_id": "scaleway/glm-5.2", "model_name": "Glm 5.2", "provider_id": "scaleway", "provider_name": "Scaleway", "input_cost_per_million": 1.7999999999999998, "output_cost_per_million": 5.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 256000, "max_output_tokens": 32768, "max_tokens": 32768, "supports_reasoning": true, "model_id": "scaleway/google/gemma-4-26b-a4b-it", "model_name": "Gemma 4 26B A4B It", "provider_id": "scaleway", "provider_name": "Scaleway", "input_cost_per_million": 0.25, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 7e-7, "max_input_tokens": 22000, "max_output_tokens": 16384, "deprecation_date": "2026-08-09", "max_tokens": 16384, "supports_reasoning": true, "model_id": "scaleway/hcompany/holo2-30b-a3b", "model_name": "Holo2 30B A3B", "provider_id": "scaleway", "provider_name": "Scaleway", "input_cost_per_million": 0.3, "output_cost_per_million": 0.7, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 256000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "scaleway/mistralai/mistral-medium-3.5-128b", "model_name": "Mistral Medium 3.5 128B", "provider_id": "scaleway", "provider_name": "Scaleway", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000036, "max_input_tokens": 256000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_reasoning": true, "model_id": "scaleway/qwen/qwen3.5-397b-a17b", "model_name": "Qwen3.5 397B A17B", "provider_id": "scaleway", "provider_name": "Scaleway", "input_cost_per_million": 0.6, "output_cost_per_million": 3.5999999999999996, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 256000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_reasoning": true, "model_id": "scaleway/qwen/qwen3.6-35b-a3b", "model_name": "Qwen3.6 35B A3B", "provider_id": "scaleway", "provider_name": "Scaleway", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 6.1e-7, "output_cost_per_token": 0.00000198, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://scx.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "scx-ai/GLM-5.2", "model_name": "GLM 5.2", "provider_id": "scx-ai", "provider_name": "Scx AI", "input_cost_per_million": 0.61, "output_cost_per_million": 1.9800000000000002, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000165, "output_cost_per_token": 0.00000499, "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://scx.ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "scx-ai/Qwen3.8-Max", "model_name": "Qwen3.8 Max", "provider_id": "scx-ai", "provider_name": "Scx AI", "input_cost_per_million": 1.6500000000000001, "output_cost_per_million": 4.989999999999999, "cache_read_cost_per_token": 2.1e-7, "cache_read_cost_per_million": 0.21, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "snowflake/claude-3-7-sonnet", "model_name": "Claude 3 7 Sonnet", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "prompt_cache_min_tokens": 1024, "model_id": "snowflake/claude-4-opus", "model_name": "Claude 4 Opus", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_reasoning": true, "supports_system_messages": true, "model_id": "snowflake/deepseek-r1", "model_name": "DeepSeek R1", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 1.35, "output_cost_per_million": 5.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 300000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "snowflake/openai-gpt-5", "model_name": "Openai GPT-5", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 1000000, "max_output_tokens": 384000, "input_cost_per_token_cache_hit": 2.8e-9, "max_tokens": 384000, "source": "https://www.tencentcloud.com/products/tokenhub", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_reasoning": true, "model_id": "tencent/deepseek-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "tencent", "provider_name": "Tencent", "input_cost_per_million": 0.14, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 2.8e-9, "cache_read_cost_per_million": 0.0028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 4.35e-7, "output_cost_per_token": 8.7e-7, "max_input_tokens": 1000000, "max_output_tokens": 384000, "input_cost_per_token_cache_hit": 3.625e-9, "max_tokens": 384000, "source": "https://www.tencentcloud.com/products/tokenhub", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_reasoning": true, "model_id": "tencent/deepseek-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "tencent", "provider_name": "Tencent", "input_cost_per_million": 0.435, "output_cost_per_million": 0.87, "cache_read_cost_per_token": 3.625e-9, "cache_read_cost_per_million": 0.003625, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "input_cost_per_token_cache_hit": 6e-8, "source": "https://www.tencentcloud.com/products/tokenhub", "supported_endpoints": [ "/v1/chat/completions" ], "supports_adaptive_thinking": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "model_id": "tencent/minimax-m3", "model_name": "Minimax M3", "provider_id": "tencent", "provider_name": "Tencent", "max_output_tokens": 0, "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter", "model_id": "tensormesh/deepseek-ai/DeepSeek-V4-Flash", "model_name": "DeepSeek V4 Flash", "provider_id": "tensormesh", "provider_name": "Tensormesh", "input_cost_per_million": 0.14, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 5.6e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter", "model_id": "tensormesh/google/gemma-4-31B-it", "model_name": "Gemma 4 31B It", "provider_id": "tensormesh", "provider_name": "Tensormesh", "input_cost_per_million": 0.14, "output_cost_per_million": 0.56, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 202752, "max_output_tokens": 202752, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter", "model_id": "tensormesh/lukealonso/GLM-5.1-NVFP4-MTP", "model_name": "GLM 5.1 NVFP4 MTP", "provider_id": "tensormesh", "provider_name": "Tensormesh", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 196608, "max_output_tokens": 196608, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter", "model_id": "tensormesh/MiniMaxAI/MiniMax-M2.5", "model_name": "MiniMax M2.5", "provider_id": "tensormesh", "provider_name": "Tensormesh", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 9.6e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 32768, "max_output_tokens": 32768, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter", "model_id": "tensormesh/moonshotai/Kimi-K2.6", "model_name": "Kimi K2.6", "provider_id": "tensormesh", "provider_name": "Tensormesh", "input_cost_per_million": 0.96, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter", "model_id": "tensormesh/openai/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "tensormesh", "provider_name": "Tensormesh", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 7e-8, "output_cost_per_token": 2.8e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter", "model_id": "tensormesh/openai/gpt-oss-20b", "model_name": "GPT Oss 20B", "provider_id": "tensormesh", "provider_name": "Tensormesh", "input_cost_per_million": 0.07, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000036, "max_input_tokens": 262144, "max_output_tokens": 262144, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter", "model_id": "tensormesh/Qwen/Qwen3.5-397B-A17B-FP8", "model_name": "Qwen3.5 397B A17B FP8", "provider_id": "tensormesh", "provider_name": "Tensormesh", "input_cost_per_million": 0.6, "output_cost_per_million": 3.5999999999999996, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 3.2e-7, "output_cost_per_token": 0.0000032, "max_input_tokens": 262144, "max_output_tokens": 262144, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "source": "https://serverless.tensormesh.ai/v1/models/openrouter", "model_id": "tensormesh/Qwen/Qwen3.6-27B-FP8", "model_name": "Qwen3.6 27B FP8", "provider_id": "tensormesh", "provider_name": "Tensormesh", "input_cost_per_million": 0.32, "output_cost_per_million": 3.1999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000017, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-05-14", "max_tokens": 16384, "metadata": { "successor": "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813" }, "source": "https://www.together.ai/models/deepseek-v3-1", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-V3.1", "model_name": "DeepSeek V3.1", "provider_id": "together", "provider_name": "Together AI", "input_cost_per_million": 0.6, "output_cost_per_million": 1.7, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000036, "max_input_tokens": 512288, "deprecation_date": "2026-08-27", "max_tokens": 512288, "source": "https://docs.together.ai/docs/serverless-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "nvidia/nemotron-3-ultra-550b-a55b", "model_name": "Nemotron 3 Ultra 550B A55B", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.6, "output_cost_per_million": 3.5999999999999996, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_tokens": 131072, "source": "https://www.together.ai/models/gpt-oss-120b", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "openai/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 1000000, "max_tokens": 1000000, "source": "https://docs.together.ai/docs/serverless-models", "supports_reasoning": true, "model_id": "Qwen/Qwen3.6-Plus", "model_name": "Qwen3.6 Plus", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1048575, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://docs.together.ai/docs/serverless-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "zai-org/GLM-5.3", "model_name": "GLM 5.3", "provider_id": "together", "provider_name": "Together AI", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 1048575, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://docs.together.ai/docs/serverless-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "zai-org/GLM-5.3-Flash", "model_name": "GLM 5.3 Flash", "provider_id": "together", "provider_name": "Together AI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/anthropic/claude-3-7-sonnet", "model_name": "Claude 3 7 Sonnet", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 4096, "model_id": "vercel_ai_gateway/anthropic/claude-haiku-4.5", "model_name": "Claude Haiku 4.5", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "vercel_ai_gateway/anthropic/claude-opus-4", "model_name": "Claude Opus 4", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "vercel_ai_gateway/anthropic/claude-opus-4.1", "model_name": "Claude Opus 4.1", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096, "model_id": "vercel_ai_gateway/anthropic/claude-opus-4.5", "model_name": "Claude Opus 4.5", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096, "model_id": "vercel_ai_gateway/anthropic/claude-opus-4.6", "model_name": "Claude Opus 4.6", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "vercel_ai_gateway/anthropic/claude-sonnet-4", "model_name": "Claude Sonnet 4", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "vercel_ai_gateway/anthropic/claude-sonnet-4.5", "model_name": "Claude Sonnet 4.5", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 8192, "deprecation_date": "2026-05-11", "cache_creation_input_token_cost_above_1hr": 0.000006, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "claude-3-7-sonnet@20250219", "model_name": "Claude 3 7 Sonnet@ (Feb 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-06-08", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.00002, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "model_id": "claude-fable-5", "model_name": "Claude Fable 5", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-03-01", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.00002, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "model_id": "claude-fable-5-1", "model_name": "Claude Fable 5 1", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-03-01", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.00002, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_forced_tool_use": false, "supports_native_structured_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "model_id": "claude-fable-5-1@default", "model_name": "Claude Fable 5 1@default", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-06-08", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.00002, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "model_id": "claude-fable-5@default", "model_name": "Claude Fable 5@default", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-10-15", "cache_creation_input_token_cost_above_1hr": 0.000002, "max_tokens": 64000, "regional_endpoint_uplift_multiplier": 1.1, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", "supports_assistant_prefill": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_streaming": true, "prompt_cache_min_tokens": 4096, "model_id": "claude-haiku-4-5", "model_name": "Claude Haiku 4 5", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-10-15", "cache_creation_input_token_cost_above_1hr": 0.000002, "max_tokens": 64000, "regional_endpoint_uplift_multiplier": 1.1, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", "supports_assistant_prefill": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_streaming": true, "prompt_cache_min_tokens": 4096, "model_id": "claude-haiku-4-5@20251001", "model_name": "Claude Haiku 4 5@ (Oct 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "deprecation_date": "2026-05-14", "cache_creation_input_token_cost_above_1hr": 0.00003, "max_tokens": 32000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-opus-4", "model_name": "Claude Opus 4", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-11-24", "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 64000, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096, "model_id": "claude-opus-4-5", "model_name": "Claude Opus 4 5", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-11-24", "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 64000, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_streaming": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096, "model_id": "claude-opus-4-5@20251101", "model_name": "Claude Opus 4 5@ (Nov 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-02-05", "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 4096, "model_id": "claude-opus-4-6", "model_name": "Claude Opus 4 6", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-02-05", "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 4096, "model_id": "claude-opus-4-6@default", "model_name": "Claude Opus 4 6@default", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-04-16", "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 2048, "model_id": "claude-opus-4-7", "model_name": "Claude Opus 4 7", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-04-16", "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 2048, "model_id": "claude-opus-4-7@default", "model_name": "Claude Opus 4 7@default", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-05-28", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-opus-4-8", "model_name": "Claude Opus 4 8", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-05-28", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-opus-4-8@default", "model_name": "Claude Opus 4 8@default", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "deprecation_date": "2026-05-14", "cache_creation_input_token_cost_above_1hr": 0.00003, "max_tokens": 32000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-opus-4@20250514", "model_name": "Claude Opus 4@ (May 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-01-24", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "model_id": "claude-opus-5", "model_name": "Claude Opus 5", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2027-01-24", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, "model_id": "claude-opus-5@default", "model_name": "Claude Opus 5@default", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "deprecation_date": "2026-05-14", "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-sonnet-4", "model_name": "Claude Sonnet 4", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-09-29", "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_batches": 0.0000015, "max_tokens": 64000, "output_cost_per_token_batches": 0.0000075, "regional_endpoint_uplift_multiplier": 1.1, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-sonnet-4-5", "model_name": "Claude Sonnet 4 5", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-09-29", "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_batches": 0.0000015, "max_tokens": 64000, "output_cost_per_token_batches": 0.0000075, "regional_endpoint_uplift_multiplier": 1.1, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_streaming": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-sonnet-4-5@20250929", "model_name": "Claude Sonnet 4 5@ (Sep 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000006, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_output_config": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-sonnet-4-6", "model_name": "Claude Sonnet 4 6", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "regional_endpoint_uplift_multiplier": 1.1, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000006, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_output_config": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-sonnet-4-6@default", "model_name": "Claude Sonnet 4 6@default", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "deprecation_date": "2026-05-14", "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-sonnet-4@20250514", "model_name": "Claude Sonnet 4@ (May 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2026-12-24", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.000004, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-sonnet-5", "model_name": "Claude Sonnet 5", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 1000000, "max_output_tokens": 128000, "deprecation_date": "2026-12-24", "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost_above_1hr": 0.000004, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 1024, "model_id": "claude-sonnet-5@default", "model_name": "Claude Sonnet 5@default", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054, "max_input_tokens": 65336, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "us-central1" ], "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "deepseek-ai/deepseek-r1-0528-maas", "model_name": "Deepseek R1 0528 Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1.35, "output_cost_per_million": 5.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000017, "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "us-central1" ], "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "deepseek-ai/deepseek-v3.1-maas", "model_name": "Deepseek V3.1 Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.6, "output_cost_per_million": 1.7, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5.6e-7, "output_cost_per_token": 0.00000168, "max_input_tokens": 163840, "max_output_tokens": 32768, "input_cost_per_token_batches": 2.8e-7, "max_tokens": 32768, "output_cost_per_token_batches": 8.4e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "global" ], "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "deepseek-ai/deepseek-v3.2-maas", "model_name": "Deepseek V3.2 Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.56, "output_cost_per_million": 1.68, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2026-10-20", "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false, "model_id": "gemini-2.5-flash", "model_name": "Gemini 2.5 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2026-10-20", "input_cost_per_audio_token": 3e-7, "max_tokens": 65535, "output_cost_per_reasoning_token": 4e-7, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false, "model_id": "gemini-2.5-flash-lite", "model_name": "Gemini 2.5 Flash Lite", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2025-11-18", "input_cost_per_audio_token": 5e-7, "max_tokens": 65535, "output_cost_per_reasoning_token": 4e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false, "model_id": "gemini-2.5-flash-lite-preview-06-17", "model_name": "Gemini 2.5 Flash Lite Preview 06 17", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 3e-7, "max_tokens": 65535, "output_cost_per_reasoning_token": 4e-7, "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false, "model_id": "gemini-2.5-flash-lite-preview-09-2025", "model_name": "Gemini 2.5 Flash Lite Preview 09 2025", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false, "model_id": "gemini-2.5-flash-preview-09-2025", "model_name": "Gemini 2.5 Flash Preview 09 2025", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2026-10-20", "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000015, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "model_id": "gemini-2.5-pro", "model_name": "Gemini 2.5 Pro", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.000003, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 9e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000054, "cache_read_input_token_cost_priority": 9e-8, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3-flash-preview", "model_name": "Gemini 3 Flash Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "model_id": "gemini-3-pro-preview", "model_name": "Gemini 3 Pro Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "deprecation_date": "2027-05-07", "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "regional_endpoint_uplift_multiplier": 1.1, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3.1-flash-lite", "model_name": "Gemini 3.1 Flash Lite", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_audio_token": 5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3.1-flash-lite-preview", "model_name": "Gemini 3.1 Flash Lite Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3.1-pro-preview", "model_name": "Gemini 3.1 Pro Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3.1-pro-preview-customtools", "model_name": "Gemini 3.1 Pro Preview Customtools", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000009, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2027-05-19", "prompt_cache_min_tokens": 4096, "input_cost_per_audio_token": 0.0000015, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.000009, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000027, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-7, "output_cost_per_token_batches": 0.0000045, "input_cost_per_token_flex": 7.5e-7, "output_cost_per_token_flex": 0.0000045, "cache_read_input_token_cost_flex": 7.5e-8, "model_id": "gemini-3.5-flash", "model_name": "Gemini 3.5 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1.5, "output_cost_per_million": 9, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65536, "deprecation_date": "2027-07-21", "cache_read_input_token_cost_flex": 1.5e-8, "cache_read_input_token_cost_priority": 5e-8, "input_cost_per_token_batches": 1.5e-7, "input_cost_per_token_flex": 1.5e-7, "input_cost_per_token_priority": 5.4e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token_batches": 0.00000125, "output_cost_per_token_flex": 0.00000125, "output_cost_per_token_priority": 0.0000045, "regional_endpoint_uplift_multiplier": 1.1, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3.5-flash-lite", "model_name": "Gemini 3.5 Flash Lite", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.00000135, "output_cost_per_token_priority": 0.00000675, "cache_read_input_token_cost_priority": 1.35e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3.6-flash", "model_name": "Gemini 3.6 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.00000135, "output_cost_per_token_priority": 0.00000675, "cache_read_input_token_cost_priority": 1.35e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3.7-flash", "model_name": "Gemini 3.7 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.00000135, "output_cost_per_token_priority": 0.00000675, "cache_read_input_token_cost_priority": 1.35e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3.8-flash", "model_name": "Gemini 3.8 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_vision": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000009, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.0000015, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.000009, "output_cost_per_video_token": 0.0000175, "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-flash-preview", "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "video" ], "supports_audio_input": true, "supports_reasoning": true, "supports_system_messages": true, "supports_video_input": true, "model_id": "gemini-omni-flash-preview", "model_name": "Gemini Omni Flash Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1.5, "output_cost_per_million": 9, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "model_id": "gemini-robotics-er-1.5-preview", "model_name": "Gemini Robotics Er 1.5 Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "input_cost_per_token": 9e-8, "output_cost_per_token": 3.6e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", "supports_reasoning": true, "model_id": "openai/gpt-oss-120b-maas", "model_name": "GPT Oss 120B Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.09, "output_cost_per_million": 0.36, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 7e-8, "output_cost_per_token": 2.5e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_reasoning": true, "model_id": "openai/gpt-oss-20b-maas", "model_name": "GPT Oss 20B Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.07, "output_cost_per_million": 0.25, "cache_read_cost_per_token": 7e-9, "cache_read_cost_per_million": 0.007, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://docs.x.ai/developers/models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "xai/grok-4.1-fast-reasoning", "model_name": "Grok 4.1 Fast Reasoning", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "global" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "zai-org/glm-4.7-maas", "model_name": "Glm 4.7 Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032, "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models", "supported_regions": [ "global" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "zai-org/glm-5-maas", "model_name": "Glm 5 Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1, "output_cost_per_million": 3.1999999999999997, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 98304, "max_output_tokens": 32768, "max_tokens": 32768, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "deepseek-v3-2-251201", "model_name": "Deepseek V3 2 251201", "provider_id": "volcengine", "provider_name": "Volcengine", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 204800, "max_output_tokens": 131072, "max_tokens": 131072, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "glm-4-7-251222", "model_name": "Glm 4 7 251222", "provider_id": "volcengine", "provider_name": "Volcengine", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 229376, "max_output_tokens": 32768, "max_tokens": 32768, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "kimi-k2-thinking-251104", "model_name": "Kimi K2 Thinking 251104", "provider_id": "volcengine", "provider_name": "Volcengine", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_reasoning": true, "supports_tool_choice": false, "tiered_pricing": [ { "input_cost_per_token": 4.6e-7, "output_cost_per_token": 0.0000023, "range": [ 0, 32000 ] }, { "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000035, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.000007, "range": [ 128000, 256000 ] } ], "model_id": "volcengine/doubao-seed-2-0-code-preview-260215", "model_name": "Doubao Seed 2 0 Code Preview 260215", "provider_id": "volcengine", "provider_name": "Volcengine", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_reasoning": true, "supports_tool_choice": false, "tiered_pricing": [ { "input_cost_per_token": 8.7e-8, "output_cost_per_token": 5.2e-7, "range": [ 0, 32000 ] }, { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 7.8e-7, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 2.6e-7, "output_cost_per_token": 0.0000016, "range": [ 128000, 256000 ] } ], "model_id": "volcengine/doubao-seed-2-0-lite-260215", "model_name": "Doubao Seed 2 0 Lite 260215", "provider_id": "volcengine", "provider_name": "Volcengine", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_reasoning": true, "supports_tool_choice": false, "tiered_pricing": [ { "input_cost_per_token": 2.9e-8, "output_cost_per_token": 2.9e-7, "range": [ 0, 32000 ] }, { "input_cost_per_token": 5.8e-8, "output_cost_per_token": 5.8e-7, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0.0000012, "range": [ 128000, 256000 ] } ], "model_id": "volcengine/doubao-seed-2-0-mini-260215", "model_name": "Doubao Seed 2 0 Mini 260215", "provider_id": "volcengine", "provider_name": "Volcengine", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://docs.volcengine.com/docs/82379/1330310", "supports_reasoning": true, "supports_tool_choice": false, "tiered_pricing": [ { "input_cost_per_token": 4.6e-7, "output_cost_per_token": 0.0000023, "range": [ 0, 32000 ] }, { "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000035, "range": [ 32000, 128000 ] }, { "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.000007, "range": [ 128000, 256000 ] } ], "model_id": "volcengine/doubao-seed-2-0-pro-260215", "model_name": "Doubao Seed 2 0 Pro 260215", "provider_id": "volcengine", "provider_name": "Volcengine", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054, "max_input_tokens": 161000, "max_output_tokens": 161000, "supports_reasoning": true, "max_tokens": 161000, "model_id": "wandb/deepseek-ai/DeepSeek-R1-0528", "model_name": "DeepSeek R1 0528", "provider_id": "wandb", "provider_name": "Wandb", "input_cost_per_million": 1.35, "output_cost_per_million": 5.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.00000165, "max_input_tokens": 161000, "max_output_tokens": 128000, "supports_reasoning": true, "max_tokens": 128000, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/deepseek-ai/DeepSeek-V3.1", "model_name": "DeepSeek V3.1", "provider_id": "wandb", "provider_name": "Wandb", "input_cost_per_million": 0.55, "output_cost_per_million": 1.6500000000000001, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 1048576, "supports_reasoning": true, "max_tokens": 1048576, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/deepseek-ai/DeepSeek-V4-Flash", "model_name": "DeepSeek V4 Flash", "provider_id": "wandb", "provider_name": "Wandb", "max_output_tokens": 0, "input_cost_per_million": 0.14, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 7e-8, "cache_read_cost_per_million": 0.07, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 262144, "supports_reasoning": true, "max_tokens": 262144, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/deepseek-ai/DeepSeek-V4-Flash-0731", "model_name": "DeepSeek V4 Flash 0731", "provider_id": "wandb", "provider_name": "Wandb", "max_output_tokens": 0, "input_cost_per_million": 0.13, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 7e-8, "cache_read_cost_per_million": 0.07, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 0.00000115, "output_cost_per_token": 0.00000255, "max_input_tokens": 1048576, "supports_reasoning": true, "max_tokens": 1048576, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/deepseek-ai/DeepSeek-V4-Pro", "model_name": "DeepSeek V4 Pro", "provider_id": "wandb", "provider_name": "Wandb", "max_output_tokens": 0, "input_cost_per_million": 1.15, "output_cost_per_million": 2.5500000000000003, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000131, "output_cost_per_token": 0.00000396, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/deepseek-ai/DeepSeek-V4-Pro-0813", "model_name": "DeepSeek V4 Pro 0813", "provider_id": "wandb", "provider_name": "Wandb", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.31, "output_cost_per_million": 3.9600000000000004, "cache_read_cost_per_token": 4.4e-8, "cache_read_cost_per_million": 0.044, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 3.4e-7, "max_input_tokens": 262144, "supports_reasoning": true, "max_tokens": 262144, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/google/gemma-4-31B-it", "model_name": "Gemma 4 31B It", "provider_id": "wandb", "provider_name": "Wandb", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.33999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 1.5e-7, "supports_reasoning": true, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/ibm-granite/granite-4.2-8b", "model_name": "Granite 4.2 8B", "provider_id": "wandb", "provider_name": "Wandb", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.15, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 197000, "max_output_tokens": 197000, "max_tokens": 197000, "source": "https://wandb.ai/inference/coreweave/cw_MiniMaxAI_MiniMax-M2.5", "supports_reasoning": true, "model_id": "wandb/MiniMaxAI/MiniMax-M2.5", "model_name": "MiniMax M2.5", "provider_id": "wandb", "provider_name": "Wandb", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 2.3e-7, "output_cost_per_token": 9.6e-7, "max_input_tokens": 262144, "supports_reasoning": true, "max_tokens": 262144, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/MiniMaxAI/MiniMax-M3", "model_name": "MiniMax M3", "provider_id": "wandb", "provider_name": "Wandb", "max_output_tokens": 0, "input_cost_per_million": 0.22999999999999998, "output_cost_per_million": 0.96, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://wandb.ai/inference/coreweave/cw_moonshotai_Kimi-K2.5", "supports_reasoning": true, "model_id": "wandb/moonshotai/Kimi-K2.5", "model_name": "Kimi K2.5", "provider_id": "wandb", "provider_name": "Wandb", "input_cost_per_million": 0.6, "output_cost_per_million": 3, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 6.5e-7, "output_cost_per_token": 0.00000341, "max_input_tokens": 262144, "supports_reasoning": true, "max_tokens": 262144, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/moonshotai/Kimi-K2.6", "model_name": "Kimi K2.6", "provider_id": "wandb", "provider_name": "Wandb", "max_output_tokens": 0, "input_cost_per_million": 0.65, "output_cost_per_million": 3.41, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 7.1e-7, "output_cost_per_token": 0.0000035, "max_input_tokens": 262144, "supports_reasoning": true, "max_tokens": 262144, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/moonshotai/Kimi-K2.7-Code", "model_name": "Kimi K2.7 Code", "provider_id": "wandb", "provider_name": "Wandb", "max_output_tokens": 0, "input_cost_per_million": 0.71, "output_cost_per_million": 3.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000275, "max_input_tokens": 262144, "supports_reasoning": true, "max_tokens": 262144, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B", "model_name": "NVIDIA Nemotron 3 Ultra 550B A55B", "provider_id": "wandb", "provider_name": "Wandb", "max_output_tokens": 0, "input_cost_per_million": 0.75, "output_cost_per_million": 2.75, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 1e-7, "output_cost_per_token": 2.5e-7, "max_input_tokens": 262144, "supports_reasoning": true, "max_tokens": 262144, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B", "model_name": "NVIDIA Nemotron 3.5 Lightning 30B A3B", "provider_id": "wandb", "provider_name": "Wandb", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.25, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-8, "output_cost_per_token": 1.7e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "supports_reasoning": true, "max_tokens": 131072, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/openai/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "wandb", "provider_name": "Wandb", "input_cost_per_million": 0.03, "output_cost_per_million": 0.16999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-8, "output_cost_per_token": 1.3e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "supports_reasoning": true, "max_tokens": 131072, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/openai/gpt-oss-20b", "model_name": "GPT Oss 20B", "provider_id": "wandb", "provider_name": "Wandb", "input_cost_per_million": 0.03, "output_cost_per_million": 0.13, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "supports_reasoning": true, "max_tokens": 262144, "model_id": "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507", "model_name": "Qwen3 235B A22B Thinking (Jul 2025)", "provider_id": "wandb", "provider_name": "Wandb", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.09999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 262144, "supports_reasoning": true, "max_tokens": 262144, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/Qwen/Qwen3.5-35B-A3B", "model_name": "Qwen3.5 35B A3B", "provider_id": "wandb", "provider_name": "Wandb", "max_output_tokens": 0, "input_cost_per_million": 0.25, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000036, "max_input_tokens": 262144, "supports_reasoning": true, "max_tokens": 262144, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/Qwen/Qwen3.6-27B", "model_name": "Qwen3.6 27B", "provider_id": "wandb", "provider_name": "Wandb", "max_output_tokens": 0, "input_cost_per_million": 0.6, "output_cost_per_million": 3.5999999999999996, "cache_read_cost_per_token": 1.2e-7, "cache_read_cost_per_million": 0.12, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 262144, "supports_reasoning": true, "max_tokens": 262144, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/Qwen/Qwen3.6-35B-A3B", "model_name": "Qwen3.6 35B A3B", "provider_id": "wandb", "provider_name": "Wandb", "max_output_tokens": 0, "input_cost_per_million": 0.25, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "supports_reasoning": true, "max_tokens": 262144, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/Qwen/Qwen3.8-27B", "model_name": "Qwen3.8 27B", "provider_id": "wandb", "provider_name": "Wandb", "max_output_tokens": 0, "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 3, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.055, "output_cost_per_token": 0.2, "max_input_tokens": 131072, "max_output_tokens": 131072, "supports_reasoning": true, "max_tokens": 131072, "model_id": "wandb/zai-org/GLM-4.5", "model_name": "GLM 4.5", "provider_id": "wandb", "provider_name": "Wandb", "input_cost_per_million": 55000, "output_cost_per_million": 200000, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 7.6e-7, "output_cost_per_token": 0.00000242, "max_input_tokens": 262144, "supports_reasoning": true, "max_tokens": 262144, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/", "model_id": "wandb/zai-org/GLM-5.2", "model_name": "GLM 5.2", "provider_id": "wandb", "provider_name": "Wandb", "max_output_tokens": 0, "input_cost_per_million": 0.76, "output_cost_per_million": 2.42, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecation_date": "2026-02-28", "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-3-mini", "model_name": "Grok 3 Mini", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecation_date": "2026-02-28", "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-3-mini-beta", "model_name": "Grok 3 Mini Beta", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecation_date": "2026-02-28", "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-3-mini-fast", "model_name": "Grok 3 Mini Fast", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecation_date": "2026-02-28", "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-3-mini-fast-beta", "model_name": "Grok 3 Mini Fast Beta", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecation_date": "2026-02-28", "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-3-mini-fast-latest", "model_name": "Grok 3 Mini Fast Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecation_date": "2026-02-28", "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-3-mini-latest", "model_name": "Grok 3 Mini Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "deprecation_date": "2026-05-15", "max_tokens": 2000000, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "supports_audio_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-4-1-fast", "model_name": "Grok 4 1 Fast", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "deprecation_date": "2026-05-15", "max_tokens": 2000000, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "supports_audio_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-4-1-fast-reasoning", "model_name": "Grok 4 1 Fast Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "deprecation_date": "2026-05-15", "max_tokens": 2000000, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "supports_audio_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-4-1-fast-reasoning-latest", "model_name": "Grok 4 1 Fast Reasoning Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://docs.x.ai/docs/models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "supports_prompt_caching": true, "model_id": "grok-4.20", "model_name": "Grok 4.20", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://docs.x.ai/docs/models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "supports_prompt_caching": true, "model_id": "grok-4.20-0309-reasoning", "model_name": "Grok 4.20 0309 Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-4.20-beta-0309-reasoning", "model_name": "Grok 4.20 Beta 0309 Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://docs.x.ai/docs/models", "supported_endpoints": [ "/v1/responses" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-4.20-multi-agent", "model_name": "Grok 4.20 Multi Agent", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "supported_endpoints": [ "/v1/responses" ], "model_id": "grok-4.20-multi-agent-0309", "model_name": "Grok 4.20 Multi Agent (Sep 2003)", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "supported_endpoints": [ "/v1/responses" ], "model_id": "grok-4.20-multi-agent-beta-0309", "model_name": "Grok 4.20 Multi Agent Beta (Sep 2003)", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://docs.x.ai/docs/models", "supported_endpoints": [ "/v1/responses" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-4.20-multi-agent-latest", "model_name": "Grok 4.20 Multi Agent Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://docs.x.ai/docs/models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "supports_prompt_caching": true, "model_id": "grok-4.20-reasoning", "model_name": "Grok 4.20 Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://docs.x.ai/docs/models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "supports_prompt_caching": true, "model_id": "grok-4.20-reasoning-latest", "model_name": "Grok 4.20 Reasoning Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_tokens": 1000000, "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4.3", "model_name": "Grok 4.3", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_tokens": 1000000, "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4.3-latest", "model_name": "Grok 4.3 Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 500000, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 500000, "output_cost_per_token_above_200k_tokens": 0.000012, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4.5", "model_name": "Grok 4.5", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 500000, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 500000, "output_cost_per_token_above_200k_tokens": 0.000012, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4.5-latest", "model_name": "Grok 4.5 Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 500000, "cache_read_input_token_cost_above_200k_tokens": 0.000001, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 500000, "output_cost_per_token_above_200k_tokens": 0.000012, "source": "https://docs.x.ai/developers/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4.6", "model_name": "Grok 4.6", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000002, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "input_cost_per_token_above_200k_tokens": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-build-0.1", "model_name": "Grok Build 0.1", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1, "output_cost_per_million": 2, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 500000, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 500000, "output_cost_per_token_above_200k_tokens": 0.000012, "source": "https://docs.x.ai/developers/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-build-latest", "model_name": "Grok Build Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000002, "max_input_tokens": 256000, "max_output_tokens": 256000, "deprecation_date": "2026-05-15", "max_tokens": 256000, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "input_cost_per_token_above_200k_tokens": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-code-fast", "model_name": "Grok Code Fast", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1, "output_cost_per_million": 2, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000002, "max_input_tokens": 256000, "max_output_tokens": 256000, "deprecation_date": "2026-05-15", "max_tokens": 256000, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "input_cost_per_token_above_200k_tokens": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-code-fast-1", "model_name": "Grok Code Fast 1", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1, "output_cost_per_million": 2, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000002, "max_input_tokens": 256000, "max_output_tokens": 256000, "deprecation_date": "2026-05-15", "max_tokens": 256000, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "input_cost_per_token_above_200k_tokens": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "model_id": "grok-code-fast-1-0825", "model_name": "Grok Code Fast 1 0825", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1, "output_cost_per_million": 2, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 200000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "model_id": "zai/glm-4.6", "model_name": "Glm 4.6", "provider_id": "zai", "provider_name": "Zai", "input_cost_per_million": 0.6, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 200000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "model_id": "zai/glm-4.7", "model_name": "Glm 4.7", "provider_id": "zai", "provider_name": "Zai", "input_cost_per_million": 0.6, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 200000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "model_id": "zai/glm-4.7-flash", "model_name": "Glm 4.7 Flash", "provider_id": "zai", "provider_name": "Zai", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032, "max_input_tokens": 200000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "model_id": "zai/glm-5", "model_name": "Glm 5", "provider_id": "zai", "provider_name": "Zai", "input_cost_per_million": 1, "output_cost_per_million": 3.1999999999999997, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "model_id": "zai/glm-5-code", "model_name": "Glm 5 Code", "provider_id": "zai", "provider_name": "Zai", "input_cost_per_million": 1.2, "output_cost_per_million": 5, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "model_id": "zai/glm-5.1", "model_name": "Glm 5.1", "provider_id": "zai", "provider_name": "Zai", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1000000, "max_output_tokens": 128000, "source": "https://docs.z.ai/guides/overview/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "zai/glm-5.2", "model_name": "Glm 5.2", "provider_id": "zai", "provider_name": "Zai", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "max_input_tokens": 1000000, "max_output_tokens": 128000, "source": "https://docs.z.ai/guides/overview/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "zai/glm-5.3", "model_name": "Glm 5.3", "provider_id": "zai", "provider_name": "Zai", "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 1048576, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "model_id": "zai/glm-5.3-flash", "model_name": "Glm 5.3 Flash", "provider_id": "zai", "provider_name": "Zai", "input_cost_per_million": 0.15, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false } ]