[ { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "jamba-large-1.6", "model_name": "Jamba Large 1.6", "provider_id": "ai21", "provider_name": "AI21 Labs", "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": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "jamba-large-1.7", "model_name": "Jamba Large 1.7", "provider_id": "ai21", "provider_name": "AI21 Labs", "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": 2e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "jamba-mini-1.6", "model_name": "Jamba Mini 1.6", "provider_id": "ai21", "provider_name": "AI21 Labs", "input_cost_per_million": 0.19999999999999998, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "jamba-mini-1.7", "model_name": "Jamba Mini 1.7", "provider_id": "ai21", "provider_name": "AI21 Labs", "input_cost_per_million": 0.19999999999999998, "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_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": 0.000003, "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, "tool_use_system_prompt_tokens": 159, "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": 2.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 200000, "max_output_tokens": 4096, "cache_creation_input_token_cost_above_1hr": 0.000006, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 264, "model_id": "claude-3-haiku-20240307", "model_name": "Claude 3 Haiku", "provider_id": "anthropic", "provider_name": "Anthropic", "input_cost_per_million": 0.25, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 3e-7, "cache_write_cost_per_million": 0.3, "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": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 4096, "deprecation_date": "2026-05-01", "cache_creation_input_token_cost_above_1hr": 0.000006, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 395, "model_id": "claude-3-opus-20240229", "model_name": "Claude 3 Opus (Feb 2024)", "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, "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, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": 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, "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, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": 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, "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, "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", "deprecation_date": 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_tool_choice": true, "tool_use_system_prompt_tokens": 159, "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": "2026-05-14", "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, "tool_use_system_prompt_tokens": 159, "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, "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_minimal_reasoning_effort": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": 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, "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_tool_choice": true, "tool_use_system_prompt_tokens": 346, "provider_specific_entry": { "us": 1.1, "fast": 6 }, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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", "deprecation_date": 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, "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_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "provider_specific_entry": { "us": 1.1, "fast": 6 }, "supports_minimal_reasoning_effort": true, "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", "deprecation_date": 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, "tool_use_system_prompt_tokens": 159, "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, "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, "supports_web_search": true, "tool_use_system_prompt_tokens": 346, "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", "deprecation_date": 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, "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, "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", "deprecation_date": 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, "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, "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", "deprecation_date": 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, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": true, "supports_tool_choice": true, "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", "deprecation_date": 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": 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 }, "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, "tool_use_system_prompt_tokens": 159, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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", "deprecation_date": 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": 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 }, "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_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 159, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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", "deprecation_date": 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, "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, "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", "deprecation_date": 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, "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, "tool_use_system_prompt_tokens": 346, "supports_minimal_reasoning_effort": true, "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", "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": 8192, "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", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000114, "output_cost_per_token": 0.00000456, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", "supports_tool_choice": true, "model_id": "azure_ai/deepseek-v3", "model_name": "DeepSeek V3", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1400000000000001, "output_cost_per_million": 4.5600000000000005, "cache_read_cost_per_token": 0, "cache_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": 0.00000114, "output_cost_per_token": 0.00000456, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", "supports_tool_choice": true, "model_id": "azure_ai/deepseek-v3-0324", "model_name": "Deepseek V3 0324", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1400000000000001, "output_cost_per_million": 4.5600000000000005, "cache_read_cost_per_token": 0, "cache_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", "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, "supports_response_schema": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/global/grok-3", "model_name": "Grok 3", "provider_id": "azure", "provider_name": "Microsoft Azure", "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_vision": 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, "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", "deprecation_date": null, "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, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "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", "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_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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "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", "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": 400000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 1.5e-7, "cache_read_input_token_cost_priority": 1.5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 3e-7, "input_cost_per_token_above_272k_tokens": 0.0000015, "input_cost_per_token_priority": 0.0000015, "input_cost_per_token_above_272k_tokens_priority": 0.000003, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00000675, "output_cost_per_token_priority": 0.000009, "output_cost_per_token_above_272k_tokens_priority": 0.0000135, "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_service_tier": 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-5.4-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", "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": 400000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 1.5e-7, "cache_read_input_token_cost_priority": 1.5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 3e-7, "input_cost_per_token_above_272k_tokens": 0.0000015, "input_cost_per_token_priority": 0.0000015, "input_cost_per_token_above_272k_tokens_priority": 0.000003, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00000675, "output_cost_per_token_priority": 0.000009, "output_cost_per_token_above_272k_tokens_priority": 0.0000135, "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_service_tier": 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-5.4-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", "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": 400000, "max_output_tokens": 128000, "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": 0.000001875, "output_cost_per_token_priority": 0.0000025, "output_cost_per_token_above_272k_tokens_priority": 0.00000375, "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_service_tier": 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-5.4-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", "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": 400000, "max_output_tokens": 128000, "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": 0.000001875, "output_cost_per_token_priority": 0.0000025, "output_cost_per_token_above_272k_tokens_priority": 0.00000375, "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_service_tier": 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-5.4-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", "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, "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_service_tier": 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", "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, "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_service_tier": 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", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "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": 131072, "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supports_tool_choice": true, "model_id": "azure_ai/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "azure", "provider_name": "Microsoft Azure", "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_response_schema": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-3", "model_name": "Grok 3", "provider_id": "azure", "provider_name": "Microsoft Azure", "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_vision": 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, "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", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4", "model_name": "Grok 4", "provider_id": "azure", "provider_name": "Microsoft Azure", "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": 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": 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_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4-1-fast-non-reasoning", "model_name": "Grok 4 1 Fast Non 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_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_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, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4-fast-non-reasoning", "model_name": "Grok 4 Fast Non 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_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://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4-fast-reasoning", "model_name": "Grok 4 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_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-code-fast-1", "model_name": "Grok Code Fast 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "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_vision": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 7e-7, "max_input_tokens": 70000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure_ai/jamba-instruct", "model_name": "Jamba Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.5, "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", "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": 6e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/kimi-k2-5-now-in-microsoft-foundry/4492321", "supports_tool_choice": true, "supports_video_input": true, "model_id": "azure_ai/kimi-k2.5", "model_name": "Kimi K2.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "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, "input_cost_per_token": 3.7e-7, "output_cost_per_token": 3.7e-7, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview", "supports_tool_choice": true, "model_id": "azure_ai/Llama-3.2-11B-Vision-Instruct", "model_name": "Llama 3.2 11B Vision Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.37, "output_cost_per_million": 0.37, "cache_read_cost_per_token": 0, "cache_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": 0.00000204, "output_cost_per_token": 0.00000204, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview", "supports_tool_choice": true, "model_id": "azure_ai/Llama-3.2-90B-Vision-Instruct", "model_name": "Llama 3.2 90B Vision Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.04, "output_cost_per_million": 2.04, "cache_read_cost_per_token": 0, "cache_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": 7.1e-7, "output_cost_per_token": 7.1e-7, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview", "supports_tool_choice": true, "model_id": "azure_ai/Llama-3.3-70B-Instruct", "model_name": "Llama 3.3 70B Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.71, "output_cost_per_million": 0.71, "cache_read_cost_per_token": 0, "cache_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": 0.00000141, "output_cost_per_token": 3.5e-7, "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", "supports_tool_choice": true, "model_id": "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8", "model_name": "Llama 4 Maverick 17B 128E Instruct FP8", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.4100000000000001, "output_cost_per_million": 0.35, "cache_read_cost_per_token": 0, "cache_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": 2e-7, "output_cost_per_token": 7.8e-7, "max_input_tokens": 10000000, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", "supports_tool_choice": true, "model_id": "azure_ai/Llama-4-Scout-17B-16E-Instruct", "model_name": "Llama 4 Scout 17B 16E Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "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_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 }, { "input_cost_per_token": 0.0000011, "output_cost_per_token": 3.7e-7, "max_input_tokens": 8192, "max_output_tokens": 2048, "max_tokens": 2048, "supports_tool_choice": true, "model_id": "azure_ai/Meta-Llama-3-70B-Instruct", "model_name": "Meta Llama 3 70B Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1, "output_cost_per_million": 0.37, "cache_read_cost_per_token": 0, "cache_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": 0.00000533, "output_cost_per_token": 0.000016, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true, "model_id": "azure_ai/Meta-Llama-3.1-405B-Instruct", "model_name": "Meta Llama 3.1 405B Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.33, "output_cost_per_million": 16, "cache_read_cost_per_token": 0, "cache_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": 0.00000268, "output_cost_per_token": 0.00000354, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true, "model_id": "azure_ai/Meta-Llama-3.1-70B-Instruct", "model_name": "Meta Llama 3.1 70B Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.68, "output_cost_per_million": 3.54, "cache_read_cost_per_token": 0, "cache_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-7, "output_cost_per_token": 6.1e-7, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true, "model_id": "azure_ai/Meta-Llama-3.1-8B-Instruct", "model_name": "Meta Llama 3.1 8B Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.3, "output_cost_per_million": 0.61, "cache_read_cost_per_token": 0, "cache_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": 4e-8, "output_cost_per_token": 4e-8, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", "supports_tool_choice": true, "model_id": "azure_ai/ministral-3b", "model_name": "Ministral 3B", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.04, "output_cost_per_million": 0.04, "cache_read_cost_per_token": 0, "cache_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": 0.000004, "output_cost_per_token": 0.000012, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "azure_ai/mistral-large", "model_name": "Mistral Large", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", "supports_tool_choice": true, "model_id": "azure_ai/mistral-large-2407", "model_name": "Mistral Large (Jul 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 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, "supports_vision": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 256000, "max_output_tokens": 8191, "max_tokens": 8191, "source": "https://azure.microsoft.com/en-us/blog/introducing-mistral-large-3-in-microsoft-foundry-open-capable-and-ready-for-production-workloads/", "supports_tool_choice": true, "model_id": "azure_ai/mistral-large-3", "model_name": "Mistral Large 3", "provider_id": "azure", "provider_name": "Microsoft Azure", "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_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", "supports_tool_choice": true, "model_id": "azure_ai/mistral-large-latest", "model_name": "Mistral Large", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 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": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 131072, "max_output_tokens": 8191, "max_tokens": 8191, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "azure_ai/mistral-medium-2505", "model_name": "Mistral Medium (May 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.39999999999999997, "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_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": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "azure_ai/mistral-small", "model_name": "Mistral Small", "provider_id": "azure", "provider_name": "Microsoft Azure", "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, "supports_vision": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "azure_ai/mistral-small-2503", "model_name": "Mistral Small (Mar 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "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 }, { "supports_vision": false, "input_cost_per_token": 1.7e-7, "output_cost_per_token": 6.8e-7, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3-medium-128k-instruct", "model_name": "Phi 3 Medium 128k Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.16999999999999998, "output_cost_per_million": 0.6799999999999999, "cache_read_cost_per_token": 0, "cache_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": false, "input_cost_per_token": 1.7e-7, "output_cost_per_token": 6.8e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3-medium-4k-instruct", "model_name": "Phi 3 Medium 4k Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.16999999999999998, "output_cost_per_million": 0.6799999999999999, "cache_read_cost_per_token": 0, "cache_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": false, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 5.2e-7, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3-mini-128k-instruct", "model_name": "Phi 3 Mini 128k Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.13, "output_cost_per_million": 0.52, "cache_read_cost_per_token": 0, "cache_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": false, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 5.2e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3-mini-4k-instruct", "model_name": "Phi 3 Mini 4k Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.13, "output_cost_per_million": 0.52, "cache_read_cost_per_token": 0, "cache_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": false, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3-small-128k-instruct", "model_name": "Phi 3 Small 128k Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "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_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3-small-8k-instruct", "model_name": "Phi 3 Small 8k Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "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_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": 5.2e-7, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3.5-mini-instruct", "model_name": "Phi 3.5 Mini Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.13, "output_cost_per_million": 0.52, "cache_read_cost_per_token": 0, "cache_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": false, "input_cost_per_token": 1.6e-7, "output_cost_per_token": 6.4e-7, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3.5-MoE-instruct", "model_name": "Phi 3.5 MoE Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.16, "output_cost_per_million": 0.64, "cache_read_cost_per_token": 0, "cache_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": 1.3e-7, "output_cost_per_token": 5.2e-7, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3.5-vision-instruct", "model_name": "Phi 3.5 Vision Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.13, "output_cost_per_million": 0.52, "cache_read_cost_per_token": 0, "cache_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": 1.25e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495", "supports_tool_choice": true, "model_id": "azure_ai/Phi-4", "model_name": "Phi 4", "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_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, "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", "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": 0.000003, "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": 0.00000275, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-02-27", "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-2024-08-06", "model_name": "GPT-4o (Aug 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 11, "cache_read_cost_per_token": 0.000001375, "cache_read_cost_per_million": 1.375, "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": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-03-01", "max_tokens": 16384, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-2024-11-20", "model_name": "GPT-4o (Nov 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 11, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0.00000138, "cache_write_cost_per_million": 1.38, "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": 1.65e-7, "output_cost_per_token": 6.6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-mini-2024-07-18", "model_name": "GPT-4o mini (Jul 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.165, "output_cost_per_million": 0.66, "cache_read_cost_per_token": 8.3e-8, "cache_read_cost_per_million": 0.083, "cache_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, "input_cost_per_token": 6.6e-7, "output_cost_per_token": 0.00000264, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3.3e-7, "input_cost_per_audio_token": 0.000011, "max_tokens": 4096, "output_cost_per_audio_token": 0.000022, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17", "model_name": "GPT-4o Mini Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.66, "output_cost_per_million": 2.64, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000022, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.000022, "input_cost_per_audio_token": 0.00011, "max_tokens": 4096, "output_cost_per_audio_token": 0.00022, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-realtime-preview-2024-10-01", "model_name": "GPT-4o Realtime Preview (Oct 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 22, "cache_read_cost_per_token": 0.00000275, "cache_read_cost_per_million": 2.75, "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": 0.0000055, "output_cost_per_token": 0.000022, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_read_input_audio_token_cost": 0.0000025, "input_cost_per_audio_token": 0.000044, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-realtime-preview-2024-12-17", "model_name": "GPT-4o Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 22, "cache_read_cost_per_token": 0.00000275, "cache_read_cost_per_million": 2.75, "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": 0.000001375, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "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", "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": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "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", "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": 5.5e-8, "output_cost_per_token": 4.4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "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", "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": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "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, "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", "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": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 128000, "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, "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", "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": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "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", "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": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "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", "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": 0.0000165, "output_cost_per_token": 0.000066, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/eu/o1-2024-12-17", "model_name": "o1 (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 16.5, "output_cost_per_million": 66, "cache_read_cost_per_token": 0.00000825, "cache_read_cost_per_million": 8.25, "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_vision": false, "input_cost_per_token": 0.00000121, "output_cost_per_token": 0.00000484, "max_input_tokens": 200000, "max_output_tokens": 100000, "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", "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": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-02-27", "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/global-standard/gpt-4o-2024-08-06", "model_name": "GPT-4o (Aug 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "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": 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": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-03-01", "max_tokens": 16384, "supports_tool_choice": true, "model_id": "azure/global-standard/gpt-4o-2024-11-20", "model_name": "GPT-4o (Nov 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "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": 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": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "model_id": "azure/global-standard/gpt-4o-mini", "model_name": "GPT-4o mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "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_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": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-02-27", "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/global/gpt-4o-2024-08-06", "model_name": "GPT-4o (Aug 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "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": 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": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-03-01", "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/global/gpt-4o-2024-11-20", "model_name": "GPT-4o (Nov 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "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": 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, "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, "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", "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": 128000, "max_output_tokens": 128000, "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, "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", "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, "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", "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, "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", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 4097, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-3.5-turbo", "model_name": "GPT 3.5T", "provider_id": "azure", "provider_name": "Microsoft Azure", "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, "supports_parallel_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 16384, "max_output_tokens": 4096, "deprecation_date": "2025-03-31", "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-3.5-turbo-0125", "model_name": "GPT-3.5 Turbo 0125", "provider_id": "azure", "provider_name": "Microsoft Azure", "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 4097, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-35-turbo", "model_name": "GPT-35 Turbo", "provider_id": "azure", "provider_name": "Microsoft Azure", "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, "supports_parallel_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 16384, "max_output_tokens": 4096, "deprecation_date": "2025-05-31", "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-35-turbo-0125", "model_name": "GPT-35 Turbo 0125", "provider_id": "azure", "provider_name": "Microsoft Azure", "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000002, "max_input_tokens": 16384, "max_output_tokens": 4096, "deprecation_date": "2025-03-31", "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-35-turbo-1106", "model_name": "GPT-35 Turbo (Jun 2011)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1, "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", "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000004, "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-35-turbo-16k", "model_name": "GPT-35 Turbo 16k", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "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": 0.000004, "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-35-turbo-16k-0613", "model_name": "GPT-35 Turbo 16k 0613", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006, "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4", "model_name": "GPT-4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-0125-preview", "model_name": "GPT-4 0125 Preview", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_per_token": 0, "cache_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": 0.00003, "output_cost_per_token": 0.00006, "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-0613", "model_name": "GPT-4 0613", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-1106-preview", "model_name": "GPT-4 1106 Preview", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_per_token": 0, "cache_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 }, { "input_cost_per_token": 0.00006, "output_cost_per_token": 0.00012, "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-32k", "model_name": "GPT-4 32k", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 60, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00006, "output_cost_per_token": 0.00012, "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-32k-0613", "model_name": "GPT-4 32k 0613", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 60, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-turbo", "model_name": "GPT-4 Turbo", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_per_token": 0, "cache_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, "supports_vision": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-turbo-2024-04-09", "model_name": "GPT-4 Turbo (Apr 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_per_token": 0, "cache_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_vision": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-turbo-vision-preview", "model_name": "GPT-4 Turbo Vision Preview", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_per_token": 0, "cache_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": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 1047576, "max_output_tokens": 32768, "input_cost_per_token_batches": 0.000001, "max_tokens": 32768, "output_cost_per_token_batches": 0.000004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": false, "model_id": "azure/gpt-4.1", "model_name": "GPT-4.1", "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", "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": 0.000008, "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 0.000001, "max_tokens": 32768, "output_cost_per_token_batches": 0.000004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": false, "model_id": "azure/gpt-4.1-2025-04-14", "model_name": "GPT-4.1 (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": true }, { "supports_function_calling": true, "supports_parallel_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": 1047576, "max_output_tokens": 32768, "input_cost_per_token_batches": 2e-7, "max_tokens": 32768, "output_cost_per_token_batches": 8e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": false, "model_id": "azure/gpt-4.1-mini", "model_name": "GPT-4.1 mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "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": true }, { "supports_function_calling": true, "supports_parallel_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": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 2e-7, "max_tokens": 32768, "output_cost_per_token_batches": 8e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": false, "model_id": "azure/gpt-4.1-mini-2025-04-14", "model_name": "GPT-4.1 mini (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "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", "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": 1047576, "max_output_tokens": 32768, "input_cost_per_token_batches": 5e-8, "max_tokens": 32768, "output_cost_per_token_batches": 2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4.1-nano", "model_name": "GPT-4.1 nano", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "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": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 5e-8, "max_tokens": 32768, "output_cost_per_token_batches": 2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4.1-nano-2025-04-14", "model_name": "GPT-4.1 nano (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "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": 0.000075, "output_cost_per_token": 0.00015, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token_batches": 0.0000375, "max_tokens": 16384, "output_cost_per_token_batches": 0.000075, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4.5-preview", "model_name": "GPT-4.5 Preview", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 75, "output_cost_per_million": 150, "cache_read_cost_per_token": 0.0000375, "cache_read_cost_per_million": 37.5, "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": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o", "model_name": "GPT-4o", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "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", "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": 0.000005, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-2024-05-13", "model_name": "GPT-4o (May 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "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_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": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-02-27", "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-2024-08-06", "model_name": "GPT-4o (Aug 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "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": 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": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-03-01", "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-2024-11-20", "model_name": "GPT-4o (Nov 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 11, "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": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00004, "max_tokens": 16384, "output_cost_per_audio_token": 0.00008, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-audio-preview-2024-12-17", "model_name": "GPT-4o Audio Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "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": 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": 1.65e-7, "output_cost_per_token": 6.6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-mini", "model_name": "GPT-4o mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.165, "output_cost_per_million": 0.66, "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": 1.65e-7, "output_cost_per_token": 6.6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-mini-2024-07-18", "model_name": "GPT-4o mini (Jul 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.165, "output_cost_per_million": 0.66, "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": false, "supports_response_schema": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00004, "max_tokens": 16384, "output_cost_per_audio_token": 0.00008, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-mini-audio-preview-2024-12-17", "model_name": "GPT-4o Mini Audio Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "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": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-mini-realtime-preview-2024-12-17", "model_name": "GPT-4o Mini Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00002, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.00002, "input_cost_per_audio_token": 0.0001, "max_tokens": 4096, "output_cost_per_audio_token": 0.0002, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-realtime-preview-2024-10-01", "model_name": "GPT-4o Realtime Preview (Oct 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 20, "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": "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": 0.000005, "output_cost_per_token": 0.00002, "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_audio_token": 0.00004, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-realtime-preview-2024-12-17", "model_name": "GPT-4o Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 20, "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": "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": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "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", "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, "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", "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": 128000, "max_output_tokens": 16384, "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", "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": 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": 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", "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, "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", "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, "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", "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, "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", "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, "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", "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, "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", "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": 272000, "max_output_tokens": 128000, "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", "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, "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, "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", "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, "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_service_tier": true, "supports_none_reasoning_effort": true, "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", "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": 128000, "max_output_tokens": 128000, "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, "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", "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, "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", "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, "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", "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, "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", "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, "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", "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, "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", "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, "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", "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, "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_service_tier": 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", "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, "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", "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, "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", "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, "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", "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, "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, "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, "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, "supports_service_tier": 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", "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, "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", "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_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_service_tier": 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", "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_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_service_tier": 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", "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": 1050000, "max_output_tokens": 128000, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "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", "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": 1050000, "max_output_tokens": 128000, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "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", "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": 1050000, "max_output_tokens": 128000, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "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", "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": 1050000, "max_output_tokens": 128000, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "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", "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, "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, "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", "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, "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", "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_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, "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_service_tier": 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", "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_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, "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_service_tier": 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", "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, "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, "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, "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": false, "supports_response_schema": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00004, "max_tokens": 16384, "output_cost_per_audio_token": 0.00008, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-audio-1.5-2026-02-23", "model_name": "GPT Audio 1.5 (Feb 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "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": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00004, "max_tokens": 16384, "output_cost_per_audio_token": 0.00008, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-audio-2025-08-28", "model_name": "GPT Audio (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "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": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00001, "max_tokens": 16384, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-audio-mini-2025-10-06", "model_name": "GPT Audio Mini (Oct 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "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_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.000004, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 4096, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-realtime-1.5-2026-02-23", "model_name": "GPT Realtime 1.5 (Feb 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4, "output_cost_per_million": 16, "cache_read_cost_per_token": 0.000004, "cache_read_cost_per_million": 4, "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": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.000004, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 4096, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-realtime-2025-08-28", "model_name": "GPT Realtime (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4, "output_cost_per_million": 16, "cache_read_cost_per_token": 0.000004, "cache_read_cost_per_million": 4, "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": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_image": 8e-7, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-realtime-mini-2025-10-06", "model_name": "GPT Realtime Mini (Oct 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "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_parallel_functions": true, "supports_vision": false, "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, "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", "deprecation_date": null, "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, "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", "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, "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", "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": "2026-04-16", "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, "max_tokens": 100000, "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", "deprecation_date": null, "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, "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", "deprecation_date": null, "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, "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", "deprecation_date": null, "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, "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", "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, "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", "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": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "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", "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": 0.0000011, "output_cost_per_token": 0.0000044, "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/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", "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": 0.0000022, "output_cost_per_token": 0.0000088, "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 0.0000011, "max_tokens": 32768, "output_cost_per_token_batches": 0.0000044, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": false, "model_id": "azure/us/gpt-4.1-2025-04-14", "model_name": "GPT-4.1 (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": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4.4e-7, "output_cost_per_token": 0.00000176, "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 2.2e-7, "max_tokens": 32768, "output_cost_per_token_batches": 8.8e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": false, "model_id": "azure/us/gpt-4.1-mini-2025-04-14", "model_name": "GPT-4.1 mini (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.44, "output_cost_per_million": 1.76, "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": 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": 1.1e-7, "output_cost_per_token": 4.4e-7, "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 6e-8, "max_tokens": 32768, "output_cost_per_token_batches": 2.2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4.1-nano-2025-04-14", "model_name": "GPT-4.1 nano (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.11, "output_cost_per_million": 0.44, "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": 0.00000275, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-02-27", "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-2024-08-06", "model_name": "GPT-4o (Aug 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 11, "cache_read_cost_per_token": 0.000001375, "cache_read_cost_per_million": 1.375, "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": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-03-01", "max_tokens": 16384, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-2024-11-20", "model_name": "GPT-4o (Nov 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 11, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0.00000138, "cache_write_cost_per_million": 1.38, "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": 1.65e-7, "output_cost_per_token": 6.6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-mini-2024-07-18", "model_name": "GPT-4o mini (Jul 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.165, "output_cost_per_million": 0.66, "cache_read_cost_per_token": 8.3e-8, "cache_read_cost_per_million": 0.083, "cache_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, "input_cost_per_token": 6.6e-7, "output_cost_per_token": 0.00000264, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3.3e-7, "input_cost_per_audio_token": 0.000011, "max_tokens": 4096, "output_cost_per_audio_token": 0.000022, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-mini-realtime-preview-2024-12-17", "model_name": "GPT-4o Mini Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.66, "output_cost_per_million": 2.64, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000022, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.000022, "input_cost_per_audio_token": 0.00011, "max_tokens": 4096, "output_cost_per_audio_token": 0.00022, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-realtime-preview-2024-10-01", "model_name": "GPT-4o Realtime Preview (Oct 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 22, "cache_read_cost_per_token": 0.00000275, "cache_read_cost_per_million": 2.75, "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": 0.0000055, "output_cost_per_token": 0.000022, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_read_input_audio_token_cost": 0.0000025, "input_cost_per_audio_token": 0.000044, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-realtime-preview-2024-12-17", "model_name": "GPT-4o Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 22, "cache_read_cost_per_token": 0.00000275, "cache_read_cost_per_million": 2.75, "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": 0.000001375, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "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", "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": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "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", "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": 5.5e-8, "output_cost_per_token": 4.4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "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", "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": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "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, "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", "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": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 128000, "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, "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", "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": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "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", "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": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "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", "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": 0.0000165, "output_cost_per_token": 0.000066, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/us/o1-2024-12-17", "model_name": "o1 (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 16.5, "output_cost_per_million": 66, "cache_read_cost_per_token": 0.00000825, "cache_read_cost_per_million": 8.25, "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": 0.0000022, "output_cost_per_token": 0.0000088, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-04-16", "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, "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", "deprecation_date": null, "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, "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", "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": 0.000003, "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": "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 }, { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_second": 0.001902, "max_tokens": 4096, "output_cost_per_second": 0.001902, "supports_tool_choice": true, "model_id": "*/1-month-commitment/cohere.command-light-text-v14", "model_name": "Cohere.command Light Text V14", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_second": 0.011, "max_tokens": 4096, "output_cost_per_second": 0.011, "supports_tool_choice": true, "model_id": "*/1-month-commitment/cohere.command-text-v14", "model_name": "Cohere.command Text V14", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_second": 0.0011416, "max_tokens": 4096, "output_cost_per_second": 0.0011416, "supports_tool_choice": true, "model_id": "*/6-month-commitment/cohere.command-light-text-v14", "model_name": "Cohere.command Light Text V14", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_second": 0.0066027, "max_tokens": 4096, "output_cost_per_second": 0.0066027, "supports_tool_choice": true, "model_id": "*/6-month-commitment/cohere.command-text-v14", "model_name": "Cohere.command Text V14", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_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": 8e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "anthropic.claude-3-5-haiku-20241022-v1:0", "model_name": "Claude 3.5 Haiku (Oct 2024)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 4, "cache_read_cost_per_token": 8e-8, "cache_read_cost_per_million": 0.08, "cache_write_cost_per_token": 0.000001, "cache_write_cost_per_million": 1, "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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_tool_choice": true, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.00003, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "cache_creation_input_token_cost_above_1hr": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000015, "model_id": "anthropic.claude-3-5-sonnet-20240620-v1:0", "model_name": "Claude 3.5 Sonnet (Jun 2024)", "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": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_tool_choice": true, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.00003, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "cache_creation_input_token_cost_above_1hr": 0.0000075, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000015, "model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0", "model_name": "Claude 3.5 Sonnet (Oct 2024)", "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": 0.0000036, "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": 2.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "anthropic.claude-3-haiku-20240307-v1:0", "model_name": "Claude 3 Haiku (Mar 2024)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.25, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 3.125e-7, "cache_write_cost_per_million": 0.3125, "model_type": "chat", "deprecation_date": 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": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "anthropic.claude-3-opus-20240229-v1:0", "model_name": "Claude 3 Opus (Feb 2024)", "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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "anthropic.claude-3-sonnet-20240229-v1:0", "model_name": "Claude 3 Sonnet (Feb 2024)", "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": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000002, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "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, "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, "tool_use_system_prompt_tokens": 346, "supports_native_streaming": true, "supports_native_structured_output": true, "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 }, { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "anthropic.claude-instant-v1", "model_name": "Claude Instant V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_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, "output_cost_per_token": 0, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_prompt_caching": false, "supports_reasoning": true, "supports_minimal_reasoning_effort": true, "supports_tool_choice": 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, "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, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": 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, "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, "tool_use_system_prompt_tokens": 159, "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, "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_minimal_reasoning_effort": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 159, "supports_native_structured_output": true, "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, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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, "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_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "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, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": 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, "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, "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, "tool_use_system_prompt_tokens": 159, "supports_native_structured_output": true, "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, "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_max_reasoning_effort": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_minimal_reasoning_effort": true, "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 }, { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024, "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "anthropic.claude-v2:1", "model_name": "Claude", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 8, "output_cost_per_million": 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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.01475, "max_tokens": 8191, "output_cost_per_second": 0.01475, "supports_tool_choice": true, "model_id": "ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1", "model_name": "Anthropic.claude Instant V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.0455, "max_tokens": 8191, "output_cost_per_second": 0.0455, "supports_tool_choice": true, "model_id": "ap-northeast-1/1-month-commitment/anthropic.claude-v2:1", "model_name": "Anthropic.claude", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.008194, "max_tokens": 8191, "output_cost_per_second": 0.008194, "supports_tool_choice": true, "model_id": "ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1", "model_name": "Anthropic.claude Instant V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.02527, "max_tokens": 8191, "output_cost_per_second": 0.02527, "supports_tool_choice": true, "model_id": "ap-northeast-1/6-month-commitment/anthropic.claude-v2:1", "model_name": "Anthropic.claude", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000223, "output_cost_per_token": 0.00000755, "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "ap-northeast-1/anthropic.claude-instant-v1", "model_name": "Anthropic.claude Instant V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.23, "output_cost_per_million": 7.55, "cache_read_cost_per_token": 0, "cache_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": 0.000008, "output_cost_per_token": 0.000024, "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "ap-northeast-1/anthropic.claude-v1", "model_name": "Anthropic.claude V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 8, "output_cost_per_million": 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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024, "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "ap-northeast-1/anthropic.claude-v2:1", "model_name": "Anthropic.claude", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 8, "output_cost_per_million": 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_function_calling": false, "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_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": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "ap-northeast-1/minimax.minimax-m2.1", "model_name": "Minimax.minimax M2.1", "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": "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, "supports_vision": true, "input_cost_per_token": 7.2e-7, "output_cost_per_token": 0.0000036, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "ap-northeast-1/moonshotai.kimi-k2.5", "model_name": "Moonshotai.kimi K2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.72, "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, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "ap-northeast-1/qwen.qwen3-coder-next", "model_name": "Qwen.qwen3 Coder Next", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.6, "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_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": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "ap-south-1/minimax.minimax-m2.1", "model_name": "Minimax.minimax M2.1", "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": "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, "supports_vision": true, "input_cost_per_token": 7.2e-7, "output_cost_per_token": 0.0000036, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "ap-south-1/moonshotai.kimi-k2.5", "model_name": "Moonshotai.kimi K2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.72, "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, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "ap-south-1/qwen.qwen3-coder-next", "model_name": "Qwen.qwen3 Coder Next", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.6, "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": 3.09e-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_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": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "ap-southeast-3/minimax.minimax-m2.1", "model_name": "Minimax.minimax M2.1", "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": "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, "input_cost_per_token": 7.2e-7, "output_cost_per_token": 0.0000036, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "ap-southeast-3/moonshotai.kimi-k2.5", "model_name": "Moonshotai.kimi K2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.72, "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, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "ap-southeast-3/qwen.qwen3-coder-next", "model_name": "Qwen.qwen3 Coder Next", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.6, "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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "apac.anthropic.claude-3-5-sonnet-20240620-v1:0", "model_name": "Claude 3.5 Sonnet (Jun 2024)", "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": 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_tool_choice": true, "model_id": "apac.anthropic.claude-3-5-sonnet-20241022-v2:0", "model_name": "Claude 3.5 Sonnet (Oct 2024)", "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": 2.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "apac.anthropic.claude-3-haiku-20240307-v1:0", "model_name": "Claude 3 Haiku (Mar 2024)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.25, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 3.125e-7, "cache_write_cost_per_million": 0.3125, "model_type": "chat", "deprecation_date": 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": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "apac.anthropic.claude-3-sonnet-20240229-v1:0", "model_name": "Claude 3 Sonnet (Feb 2024)", "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": 0.0000011, "output_cost_per_token": 0.0000055, "max_input_tokens": 200000, "max_output_tokens": 64000, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "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, "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, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": 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, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "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, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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, "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_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 200000, "max_output_tokens": 64000, "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_read_input_token_cost_above_200k_tokens": 6.6e-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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "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, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_minimal_reasoning_effort": true, "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_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, "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": 7.5e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "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": 0.075, "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, "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": 7.5e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "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": 0.075, "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, "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, "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_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 159, "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 }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "cohere.command-light-text-v14", "model_name": "Command Light Text V14", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.3, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "cohere.command-r-plus-v1:0", "model_name": "Command R+", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "cohere.command-r-v1:0", "model_name": "Command R", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "cohere.command-text-v14", "model_name": "Command Text V14", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1.5, "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_function_calling": false, "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": 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_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 }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.01635, "max_tokens": 8191, "output_cost_per_second": 0.01635, "supports_tool_choice": true, "model_id": "eu-central-1/1-month-commitment/anthropic.claude-instant-v1", "model_name": "Anthropic.claude Instant V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.0415, "max_tokens": 8191, "output_cost_per_second": 0.0415, "supports_tool_choice": true, "model_id": "eu-central-1/1-month-commitment/anthropic.claude-v2:1", "model_name": "Anthropic.claude", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.009083, "max_tokens": 8191, "output_cost_per_second": 0.009083, "supports_tool_choice": true, "model_id": "eu-central-1/6-month-commitment/anthropic.claude-instant-v1", "model_name": "Anthropic.claude Instant V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.02305, "max_tokens": 8191, "output_cost_per_second": 0.02305, "supports_tool_choice": true, "model_id": "eu-central-1/6-month-commitment/anthropic.claude-v2:1", "model_name": "Anthropic.claude", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000248, "output_cost_per_token": 0.00000838, "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "eu-central-1/anthropic.claude-instant-v1", "model_name": "Anthropic.claude Instant V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.48, "output_cost_per_million": 8.379999999999999, "cache_read_cost_per_token": 0, "cache_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": 0.000008, "output_cost_per_token": 0.000024, "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "eu-central-1/anthropic.claude-v2:1", "model_name": "Anthropic.claude", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 8, "output_cost_per_million": 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_function_calling": false, "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": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "eu-central-1/minimax.minimax-m2.1", "model_name": "Minimax.minimax M2.1", "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-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": 6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "eu-central-1/qwen.qwen3-coder-next", "model_name": "Qwen.qwen3 Coder Next", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.6, "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_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": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "eu-north-1/minimax.minimax-m2.1", "model_name": "Minimax.minimax M2.1", "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-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, "supports_vision": true, "input_cost_per_token": 7.2e-7, "output_cost_per_token": 0.0000036, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "eu-north-1/moonshotai.kimi-k2.5", "model_name": "Moonshotai.kimi K2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.72, "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, "input_cost_per_token": 3.6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "eu-south-1/minimax.minimax-m2.1", "model_name": "Minimax.minimax M2.1", "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": 6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "eu-south-1/qwen.qwen3-coder-next", "model_name": "Qwen.qwen3 Coder Next", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.6, "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": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "eu-west-1/minimax.minimax-m2.1", "model_name": "Minimax.minimax M2.1", "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": 6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "eu-west-1/qwen.qwen3-coder-next", "model_name": "Qwen.qwen3 Coder Next", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.6, "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": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "eu-west-2/minimax.minimax-m2.1", "model_name": "Minimax.minimax M2.1", "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, "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, "input_cost_per_token": 7.8e-7, "output_cost_per_token": 0.00000186, "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "eu-west-2/qwen.qwen3-coder-next", "model_name": "Qwen.qwen3 Coder Next", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.78, "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 }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 2.6e-7, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "eu-west-3/mistral.mistral-7b-instruct-v0:2", "model_name": "Mistral.mistral 7B Instruct", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.19999999999999998, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5.9e-7, "output_cost_per_token": 9.1e-7, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "eu-west-3/mistral.mixtral-8x7b-instruct-v0:1", "model_name": "Mistral.mixtral 8x7B Instruct", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.59, "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_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": 2.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "eu.anthropic.claude-3-5-haiku-20241022-v1:0", "model_name": "Claude 3.5 Haiku (Oct 2024)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.25, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 3.125e-7, "cache_write_cost_per_million": 0.3125, "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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "eu.anthropic.claude-3-5-sonnet-20240620-v1:0", "model_name": "Claude 3.5 Sonnet (Jun 2024)", "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": 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_tool_choice": true, "model_id": "eu.anthropic.claude-3-5-sonnet-20241022-v2:0", "model_name": "Claude 3.5 Sonnet (Oct 2024)", "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": 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": 2.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "eu.anthropic.claude-3-haiku-20240307-v1:0", "model_name": "Claude 3 Haiku (Mar 2024)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.25, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 3.125e-7, "cache_write_cost_per_million": 0.3125, "model_type": "chat", "deprecation_date": 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": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "eu.anthropic.claude-3-opus-20240229-v1:0", "model_name": "Claude 3 Opus (Feb 2024)", "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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "eu.anthropic.claude-3-sonnet-20240229-v1:0", "model_name": "Claude 3 Sonnet (Feb 2024)", "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": 0.0000011, "output_cost_per_token": 0.0000055, "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecation_date": "2026-10-15", "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "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, "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, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": 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, "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, "tool_use_system_prompt_tokens": 159, "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, "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_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 159, "supports_native_structured_output": true, "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, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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, "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_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "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, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": 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, "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_read_input_token_cost_above_200k_tokens": 6.6e-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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "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, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_minimal_reasoning_effort": true, "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, "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_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": 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, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "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, "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_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 159, "supports_native_structured_output": true, "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, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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, "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_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "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, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": 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, "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, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "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, "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_max_reasoning_effort": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_minimal_reasoning_effort": true, "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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "metadata": { "notes": "Anthropic via Invoke route does not currently support pdf input." }, "supports_tool_choice": true, "model_id": "invoke/anthropic.claude-3-5-sonnet-20240620-v1:0", "model_name": "Anthropic.claude 3 5 Sonnet (Jun 2024)", "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": 0.0000011, "output_cost_per_token": 0.0000055, "max_input_tokens": 200000, "max_output_tokens": 64000, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "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": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 200000, "max_output_tokens": 64000, "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_read_input_token_cost_above_200k_tokens": 6.6e-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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "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, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_minimal_reasoning_effort": true, "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, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "minimax.minimax-m2.1", "model_name": "Minimax.minimax M2.1", "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": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "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": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 256000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "mistral.devstral-2-123b", "model_name": "Devstral 2 123B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.39999999999999997, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral.mistral-7b-instruct-v0:2", "model_name": "Mistral 7B Instruct", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.15, "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 }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000009, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral.mistral-large-2407-v1:0", "model_name": "Mistral Large (Jul 2024)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 4.5e-7, "output_cost_per_token": 7e-7, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral.mixtral-8x7b-instruct-v0:1", "model_name": "Mixtral 8x7B Instruct", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.44999999999999996, "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", "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": 6e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "moonshotai.kimi-k2.5", "model_name": "Moonshotai.kimi K2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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, "input_cost_per_token": 6e-8, "output_cost_per_token": 2.4e-7, "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "supports_native_structured_output": true, "model_id": "nvidia.nemotron-nano-3-30b", "model_name": "Nvidia.nemotron Nano 3 30B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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": 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, "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": 2.2e-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, "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": 0.22, "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": 5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "qwen.qwen3-coder-next", "model_name": "Qwen.qwen3 Coder Next", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.5, "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": 7.4e-7, "output_cost_per_token": 0.00000222, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": 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": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "sa-east-1/minimax.minimax-m2.1", "model_name": "Minimax.minimax M2.1", "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": "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, "supports_vision": true, "input_cost_per_token": 7.2e-7, "output_cost_per_token": 0.0000036, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "sa-east-1/moonshotai.kimi-k2.5", "model_name": "Moonshotai.kimi K2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.72, "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, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.00000144, "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "sa-east-1/qwen.qwen3-coder-next", "model_name": "Qwen.qwen3 Coder Next", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.6, "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 }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.011, "max_tokens": 8191, "output_cost_per_second": 0.011, "supports_tool_choice": true, "model_id": "us-east-1/1-month-commitment/anthropic.claude-instant-v1", "model_name": "Anthropic.claude Instant V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.0175, "max_tokens": 8191, "output_cost_per_second": 0.0175, "supports_tool_choice": true, "model_id": "us-east-1/1-month-commitment/anthropic.claude-v2:1", "model_name": "Anthropic.claude", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.00611, "max_tokens": 8191, "output_cost_per_second": 0.00611, "supports_tool_choice": true, "model_id": "us-east-1/6-month-commitment/anthropic.claude-instant-v1", "model_name": "Anthropic.claude Instant V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.00972, "max_tokens": 8191, "output_cost_per_second": 0.00972, "supports_tool_choice": true, "model_id": "us-east-1/6-month-commitment/anthropic.claude-v2:1", "model_name": "Anthropic.claude", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "us-east-1/anthropic.claude-instant-v1", "model_name": "Anthropic.claude Instant V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024, "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "us-east-1/anthropic.claude-v1", "model_name": "Anthropic.claude V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 8, "output_cost_per_million": 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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024, "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "us-east-1/anthropic.claude-v2:1", "model_name": "Anthropic.claude", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 8, "output_cost_per_million": 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_function_calling": false, "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_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": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-east-1/minimax.minimax-m2.1", "model_name": "Minimax.minimax M2.1", "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": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-east-1/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 }, { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "us-east-1/mistral.mistral-7b-instruct-v0:2", "model_name": "Mistral.mistral 7B Instruct", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.15, "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": 7e-7, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "us-east-1/mistral.mixtral-8x7b-instruct-v0:1", "model_name": "Mistral.mixtral 8x7B Instruct", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.44999999999999996, "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", "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": 6e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-east-1/moonshotai.kimi-k2.5", "model_name": "Moonshotai.kimi K2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-east-1/qwen.qwen3-coder-next", "model_name": "Qwen.qwen3 Coder Next", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.5, "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": 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_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_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": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-east-2/minimax.minimax-m2.1", "model_name": "Minimax.minimax M2.1", "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": 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, "supports_vision": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-east-2/moonshotai.kimi-k2.5", "model_name": "Moonshotai.kimi K2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-east-2/qwen.qwen3-coder-next", "model_name": "Qwen.qwen3 Coder Next", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.5, "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, "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_pdf_input": true, "supports_tool_choice": true, "model_id": "us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0", "model_name": "Anthropic.claude 3 5 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": 3e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0", "model_name": "Anthropic.claude 3 Haiku (Mar 2024)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.3, "output_cost_per_million": 1.5, "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_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, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_pdf_input": true, "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": 0.0000033, "output_cost_per_token": 0.0000165, "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, "supports_native_structured_output": true, "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": 3.3000000000000003, "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": 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, "supports_native_structured_output": true, "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": 3.3000000000000003, "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": 0.0000036, "output_cost_per_token": 0.000018, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0", "model_name": "Anthropic.claude 3 5 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": 0.0000036, "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": "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", "deprecation_date": 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": 0.0000015, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0", "model_name": "Anthropic.claude 3 Haiku (Mar 2024)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.3, "output_cost_per_million": 1.5, "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_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, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_pdf_input": true, "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": 0.0000033, "output_cost_per_token": 0.0000165, "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, "supports_native_structured_output": true, "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": 3.3000000000000003, "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": 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, "supports_native_structured_output": true, "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": 3.3000000000000003, "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": 200000, "max_output_tokens": 64000, "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_read_input_token_cost_above_200k_tokens": 6.6e-7, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "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": 3.3000000000000003, "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 }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.011, "max_tokens": 8191, "output_cost_per_second": 0.011, "supports_tool_choice": true, "model_id": "us-west-2/1-month-commitment/anthropic.claude-instant-v1", "model_name": "Anthropic.claude Instant V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.0175, "max_tokens": 8191, "output_cost_per_second": 0.0175, "supports_tool_choice": true, "model_id": "us-west-2/1-month-commitment/anthropic.claude-v2:1", "model_name": "Anthropic.claude", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.00611, "max_tokens": 8191, "output_cost_per_second": 0.00611, "supports_tool_choice": true, "model_id": "us-west-2/6-month-commitment/anthropic.claude-instant-v1", "model_name": "Anthropic.claude Instant V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.00972, "max_tokens": 8191, "output_cost_per_second": 0.00972, "supports_tool_choice": true, "model_id": "us-west-2/6-month-commitment/anthropic.claude-v2:1", "model_name": "Anthropic.claude", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "us-west-2/anthropic.claude-instant-v1", "model_name": "Anthropic.claude Instant V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024, "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "us-west-2/anthropic.claude-v1", "model_name": "Anthropic.claude V1", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 8, "output_cost_per_million": 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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024, "max_input_tokens": 100000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "us-west-2/anthropic.claude-v2:1", "model_name": "Anthropic.claude", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 8, "output_cost_per_million": 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_function_calling": false, "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_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": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 196000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-west-2/minimax.minimax-m2.1", "model_name": "Minimax.minimax M2.1", "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": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-west-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 }, { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "us-west-2/mistral.mistral-7b-instruct-v0:2", "model_name": "Mistral.mistral 7B Instruct", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.15, "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": 7e-7, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "us-west-2/mistral.mixtral-8x7b-instruct-v0:1", "model_name": "Mistral.mixtral 8x7B Instruct", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.44999999999999996, "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", "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": 6e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-west-2/moonshotai.kimi-k2.5", "model_name": "Moonshotai.kimi K2.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 262144, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/", "model_id": "us-west-2/qwen.qwen3-coder-next", "model_name": "Qwen.qwen3 Coder Next", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.5, "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": 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_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_response_schema": true, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "us.anthropic.claude-3-5-haiku-20241022-v1:0", "model_name": "Claude 3.5 Haiku (Oct 2024)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 4, "cache_read_cost_per_token": 8e-8, "cache_read_cost_per_million": 0.08, "cache_write_cost_per_token": 0.000001, "cache_write_cost_per_million": 1, "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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "us.anthropic.claude-3-5-sonnet-20240620-v1:0", "model_name": "Claude 3.5 Sonnet (Jun 2024)", "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": 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_tool_choice": true, "model_id": "us.anthropic.claude-3-5-sonnet-20241022-v2:0", "model_name": "Claude 3.5 Sonnet (Oct 2024)", "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": 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": 2.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "us.anthropic.claude-3-haiku-20240307-v1:0", "model_name": "Claude 3 Haiku (Mar 2024)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.25, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 3.125e-7, "cache_write_cost_per_million": 0.3125, "model_type": "chat", "deprecation_date": 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": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "us.anthropic.claude-3-opus-20240229-v1:0", "model_name": "Claude 3 Opus (Feb 2024)", "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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "us.anthropic.claude-3-sonnet-20240229-v1:0", "model_name": "Claude 3 Sonnet (Feb 2024)", "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": 0.0000011, "output_cost_per_token": 0.0000055, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.0000022, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "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, "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, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": 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, "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, "tool_use_system_prompt_tokens": 159, "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, "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_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 159, "supports_native_structured_output": true, "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, "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_tool_choice": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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, "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_tool_choice": true, "supports_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "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, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": 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, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "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, "cache_creation_input_token_cost_above_1hr": 0.0000066, "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, "tool_use_system_prompt_tokens": 346, "supports_native_structured_output": true, "supports_minimal_reasoning_effort": true, "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, "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_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, "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_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_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": 8.5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "cerebras/llama-3.3-70b", "model_name": "Llama 3.3 70B", "provider_id": "cerebras", "provider_name": "Cerebras", "input_cost_per_million": 0.85, "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": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "cerebras/llama3.1-70b", "model_name": "Llama 3.1 70B", "provider_id": "cerebras", "provider_name": "Cerebras", "input_cost_per_million": 0.6, "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": 1e-7, "output_cost_per_token": 1e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "cerebras/llama3.1-8b", "model_name": "Llama 3.1 8B", "provider_id": "cerebras", "provider_name": "Cerebras", "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_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": 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, "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, "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", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 256000, "max_output_tokens": 8000, "max_tokens": 8000, "supports_tool_choice": true, "model_id": "command-a-03-2025", "model_name": "Command A 03 2025", "provider_id": "cohere", "provider_name": "Cohere", "input_cost_per_million": 2.5, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "command-light", "model_name": "Command Light", "provider_id": "cohere", "provider_name": "Cohere", "input_cost_per_million": 0.3, "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_function_calling": false, "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": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "command-r", "model_name": "Command R", "provider_id": "cohere", "provider_name": "Cohere", "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": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "command-r-08-2024", "model_name": "Command R 08 2024", "provider_id": "cohere", "provider_name": "Cohere", "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": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "command-r-plus", "model_name": "Command R+", "provider_id": "cohere", "provider_name": "Cohere", "input_cost_per_million": 2.5, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "command-r-plus-08-2024", "model_name": "Command R Plus 08 2024", "provider_id": "cohere", "provider_name": "Cohere", "input_cost_per_million": 2.5, "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_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": 3.75e-8, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://docs.cohere.com/v2/docs/command-r7b", "supports_tool_choice": true, "model_id": "command-r7b-12-2024", "model_name": "Command R7B 12 2024", "provider_id": "cohere", "provider_name": "Cohere", "input_cost_per_million": 0.15, "output_cost_per_million": 0.0375, "cache_read_cost_per_token": 0, "cache_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, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000015, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "crusoe/deepseek-ai/DeepSeek-V3-0324", "model_name": "DeepSeek V3 0324", "provider_id": "crusoe", "provider_name": "Crusoe", "input_cost_per_million": 1.5, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "crusoe/google/gemma-3-12b-it", "model_name": "Gemma 3 12B It", "provider_id": "crusoe", "provider_name": "Crusoe", "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_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "crusoe/meta-llama/Llama-3.3-70B-Instruct", "model_name": "Llama 3.3 70B Instruct", "provider_id": "crusoe", "provider_name": "Crusoe", "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_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_system_messages": true, "supports_tool_choice": true, "model_id": "crusoe/openai/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "crusoe", "provider_name": "Crusoe", "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": 0.000003, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507", "model_name": "Qwen3 235B A22B Instruct (Jul 2025)", "provider_id": "crusoe", "provider_name": "Crusoe", "input_cost_per_million": 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": 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_tool_choice": true, "model_id": "dashscope/qwen3-next-80b-a3b-instruct", "model_name": "Qwen3 Next 80B A3B Instruct", "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, "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": 0.0000016, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_tool_choice": true, "model_id": "dashscope/qwen3-vl-235b-a22b-instruct", "model_name": "Qwen3 Vl 235B A22B Instruct", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "cache_read_cost_per_token": 0, "cache_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": 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": 6.4e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "supports_tool_choice": true, "model_id": "dashscope/qwen3-vl-32b-instruct", "model_name": "Qwen3 Vl 32B Instruct", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.16, "output_cost_per_million": 0.64, "cache_read_cost_per_token": 0, "cache_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, "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, "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_reasoning": 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": 0, "cache_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": 0.00000100002, "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_reasoning": true, "supports_tool_choice": true, "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": 0, "cache_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": 0.000015000020000000002, "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_reasoning": true, "supports_tool_choice": true, "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, "cache_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": 0.000015000020000000002, "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_reasoning": true, "supports_tool_choice": true, "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, "cache_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": 0.00000500003, "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_reasoning": true, "supports_minimal_reasoning_effort": true, "supports_tool_choice": true, "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": 0, "cache_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": 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_reasoning": 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": 0, "cache_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": 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_reasoning": 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": 0, "cache_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": 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_reasoning": true, "supports_tool_choice": true, "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": 0, "cache_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": 3.0001999999999996e-7, "output_cost_per_token": 0.00000249998, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_dbu_cost_per_token": 0.000004285999999999999, "max_tokens": 65535, "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": 0.000035714, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_tool_choice": true, "model_id": "databricks-gemini-2-5-flash", "model_name": "Databricks Gemini 2 5 Flash", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 0.30001999999999995, "output_cost_per_million": 2.49998, "cache_read_cost_per_token": 0, "cache_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": 0.00000124999, "output_cost_per_token": 0.000009999990000000002, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_dbu_cost_per_token": 0.000017857, "max_tokens": 65536, "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": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_tool_choice": true, "model_id": "databricks-gemini-2-5-pro", "model_name": "Databricks Gemini 2 5 Pro", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 1.24999, "output_cost_per_million": 9.999990000000002, "cache_read_cost_per_token": 0, "cache_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": 5.0001e-7, "output_cost_per_token": 0.0000015000300000000002, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_dbu_cost_per_token": 0.000007143, "max_tokens": 4096, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000021429, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true, "model_id": "databricks-llama-2-70b-chat", "model_name": "Databricks Llama 2 70B Chat", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 0.5000100000000001, "output_cost_per_million": 1.5000300000000002, "cache_read_cost_per_token": 0, "cache_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": 5.0001e-7, "output_cost_per_token": 0.0000015000300000000002, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000007143, "max_tokens": 128000, "metadata": { "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." }, "output_dbu_cost_per_token": 0.000021429, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true, "model_id": "databricks-llama-4-maverick", "model_name": "Databricks Llama 4 Maverick", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 0.5000100000000001, "output_cost_per_million": 1.5000300000000002, "cache_read_cost_per_token": 0, "cache_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": 0.00000500003, "output_cost_per_token": 0.000015000020000000002, "max_input_tokens": 128000, "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, based on databricks Llama 3.1 70B conversion. 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/foundation-model-serving", "supports_tool_choice": true, "model_id": "databricks-meta-llama-3-1-405b-instruct", "model_name": "Databricks Meta Llama 3 1 405B Instruct", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 5.00003, "output_cost_per_million": 15.000020000000001, "cache_read_cost_per_token": 0, "cache_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": 5.0001e-7, "output_cost_per_token": 0.0000015000300000000002, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000007143, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000021429, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true, "model_id": "databricks-meta-llama-3-3-70b-instruct", "model_name": "Databricks Meta Llama 3 3 70B Instruct", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 0.5000100000000001, "output_cost_per_million": 1.5000300000000002, "cache_read_cost_per_token": 0, "cache_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": 0.00000100002, "output_cost_per_token": 0.0000029999900000000002, "max_input_tokens": 128000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000014286, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000042857, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true, "model_id": "databricks-meta-llama-3-70b-instruct", "model_name": "Databricks Meta Llama 3 70B Instruct", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 1.0000200000000001, "output_cost_per_million": 2.9999900000000004, "cache_read_cost_per_token": 0, "cache_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": 5.0001e-7, "output_cost_per_token": 0.00000100002, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_dbu_cost_per_token": 0.000007143, "max_tokens": 4096, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000014286, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true, "model_id": "databricks-mixtral-8x7b-instruct", "model_name": "Databricks Mixtral 8x7B Instruct", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 0.5000100000000001, "output_cost_per_million": 1.0000200000000001, "cache_read_cost_per_token": 0, "cache_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": 0.00000100002, "output_cost_per_token": 0.00000100002, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_dbu_cost_per_token": 0.000014286, "max_tokens": 8192, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.000014286, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true, "model_id": "databricks-mpt-30b-instruct", "model_name": "Databricks Mpt 30B Instruct", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 1.0000200000000001, "output_cost_per_million": 1.0000200000000001, "cache_read_cost_per_token": 0, "cache_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": 5.0001e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_dbu_cost_per_token": 0.000007143, "max_tokens": 8192, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0, "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true, "model_id": "databricks-mpt-7b-instruct", "model_name": "Databricks Mpt 7B Instruct", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 0.5000100000000001, "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, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000165, "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "supports_tool_choice": true, "model_id": "anthropic/claude-3-7-sonnet-latest", "model_name": "Claude 3.7 Sonnet", "provider_id": "deepinfra", "provider_name": "DeepInfra", "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000165, "output_cost_per_token": 0.0000825, "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "supports_tool_choice": true, "model_id": "anthropic/claude-4-opus", "model_name": "Claude 4 Opus", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 16.5, "output_cost_per_million": 82.5, "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": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-R1-0528", "model_name": "DeepSeek R1 0528", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.5, "output_cost_per_million": 2.1500000000000004, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "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": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-R1-0528-Turbo", "model_name": "DeepSeek R1 0528 Turbo", "provider_id": "deepinfra", "provider_name": "DeepInfra", "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": 2.7e-7, "output_cost_per_token": 2.7e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "model_name": "DeepSeek R1 Distill Qwen 32B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.27, "output_cost_per_million": 0.27, "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", "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": 40960, "max_output_tokens": 40960, "max_tokens": 40960, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-R1-Turbo", "model_name": "DeepSeek R1 Turbo", "provider_id": "deepinfra", "provider_name": "DeepInfra", "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": 2.5e-7, "output_cost_per_token": 8.8e-7, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-V3-0324", "model_name": "DeepSeek V3 0324", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.25, "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": 2.7e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-V3.1-Terminus", "model_name": "DeepSeek V3.1 Terminus", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.27, "output_cost_per_million": 1, "cache_read_cost_per_token": 2.16e-7, "cache_read_cost_per_million": 0.216, "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": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "deprecation_date": "2026-06-01", "max_tokens": 1000000, "supports_tool_choice": true, "model_id": "google/gemini-2.0-flash-001", "model_name": "Gemini 2.0 Flash 001", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.09999999999999999, "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", "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": 1e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "google/gemma-3-12b-it", "model_name": "Gemma 3 12B It", "provider_id": "deepinfra", "provider_name": "DeepInfra", "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 9e-8, "output_cost_per_token": 1.6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "google/gemma-3-27b-it", "model_name": "Gemma 3 27B It", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.09, "output_cost_per_million": 0.16, "cache_read_cost_per_token": 0, "cache_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-8, "output_cost_per_token": 8e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "google/gemma-3-4b-it", "model_name": "Gemma 3 4B It", "provider_id": "deepinfra", "provider_name": "DeepInfra", "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 8e-8, "output_cost_per_token": 9e-8, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "Gryphe/MythoMax-L2-13b", "model_name": "MythoMax L2 13B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.08, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-8, "output_cost_per_token": 2e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "meta-llama/Llama-3.2-3B-Instruct", "model_name": "Llama 3.2 3B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.02, "output_cost_per_million": 0.02, "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, "input_cost_per_token": 2.3e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "meta-llama/Llama-3.3-70B-Instruct", "model_name": "Llama 3.3 70B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.22999999999999998, "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": 3e-8, "output_cost_per_token": 6e-8, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "meta-llama/Meta-Llama-3-8B-Instruct", "model_name": "Meta Llama 3 8B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.03, "output_cost_per_million": 0.06, "cache_read_cost_per_token": 0, "cache_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": 4e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "meta-llama/Meta-Llama-3.1-70B-Instruct", "model_name": "Meta Llama 3.1 70B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.39999999999999997, "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": 3e-8, "output_cost_per_token": 5e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct", "model_name": "Meta Llama 3.1 8B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.03, "output_cost_per_million": 0.049999999999999996, "cache_read_cost_per_token": 0, "cache_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": 1.4e-7, "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "model_id": "microsoft/phi-4", "model_name": "Phi 4", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.07, "output_cost_per_million": 0.14, "cache_read_cost_per_token": 0, "cache_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-8, "output_cost_per_token": 4e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "mistralai/Mistral-Nemo-Instruct-2407", "model_name": "Mistral Nemo Instruct (Jul 2024)", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.02, "output_cost_per_million": 0.04, "cache_read_cost_per_token": 0, "cache_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": 7.5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "model_name": "Mistral Small 3.2 24B Instruct (Jun 2025)", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.075, "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": 0.000001, "output_cost_per_token": 0.000001, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "NousResearch/Hermes-3-Llama-3.1-405B", "model_name": "Hermes 3 Llama 3.1 405B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 1, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct", "model_name": "Llama 3.1 Nemotron 70B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.6, "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": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "nvidia/Llama-3.3-Nemotron-Super-49B-v1.5", "model_name": "Llama 3.3 Nemotron Super 49B V1.5", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.09999999999999999, "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": 4e-8, "output_cost_per_token": 1.6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "nvidia/NVIDIA-Nemotron-Nano-9B-v2", "model_name": "NVIDIA Nemotron Nano 9B V2", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.04, "output_cost_per_million": 0.16, "cache_read_cost_per_token": 0, "cache_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": 1.2e-7, "output_cost_per_token": 3.9e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "model_id": "Qwen/Qwen2.5-72B-Instruct", "model_name": "Qwen2.5 72B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.12, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "Qwen/Qwen2.5-VL-32B-Instruct", "model_name": "Qwen2.5 VL 32B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "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_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": 40960, "max_output_tokens": 40960, "max_tokens": 40960, "supports_tool_choice": true, "model_id": "Qwen/Qwen3-14B", "model_name": "Qwen3 14B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "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": 1.8e-7, "output_cost_per_token": 5.4e-7, "max_input_tokens": 40960, "max_output_tokens": 40960, "max_tokens": 40960, "supports_tool_choice": true, "model_id": "Qwen/Qwen3-235B-A22B", "model_name": "Qwen3 235B A22B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.18, "output_cost_per_million": 0.54, "cache_read_cost_per_token": 0, "cache_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": 6e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "model_name": "Qwen3 235B A22B Instruct (Jul 2025)", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.09, "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": 8e-8, "output_cost_per_token": 2.9e-7, "max_input_tokens": 40960, "max_output_tokens": 40960, "max_tokens": 40960, "supports_tool_choice": true, "model_id": "Qwen/Qwen3-30B-A3B", "model_name": "Qwen3 30B A3B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.08, "output_cost_per_million": 0.29, "cache_read_cost_per_token": 0, "cache_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": 1e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 40960, "max_output_tokens": 40960, "max_tokens": 40960, "supports_tool_choice": true, "model_id": "Qwen/Qwen3-32B", "model_name": "Qwen3 32B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.09999999999999999, "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": 4e-7, "output_cost_per_token": 0.0000016, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "model_name": "Qwen3 Coder 480B A35B Instruct", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "cache_read_cost_per_token": 0, "cache_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": 2.9e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", "model_name": "Qwen3 Coder 480B A35B Instruct Turbo", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.29, "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": 1.5e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "Qwen/QwQ-32B", "model_name": "QwQ 32B", "provider_id": "deepinfra", "provider_name": "DeepInfra", "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "zai-org/GLM-4.5", "model_name": "GLM 4.5", "provider_id": "deepinfra", "provider_name": "DeepInfra", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "cache_read_cost_per_token": 0, "cache_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_response_schema": true, "input_cost_per_token": 2.8e-7, "output_cost_per_token": 4.2e-7, "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "deepseek-chat", "model_name": "Deepseek Chat", "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": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "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": 8192, "input_cost_per_token_cache_hit": 2.8e-8, "max_tokens": 8192, "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_system_messages": true, "supports_tool_choice": true, "model_id": "deepseek/deepseek-chat", "model_name": "Deepseek Chat", "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": true, "supports_vision": false }, { "supports_function_calling": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_token_cache_hit": 1.4e-8, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "deepseek/deepseek-coder", "model_name": "Deepseek Coder", "provider_id": "deepseek", "provider_name": "DeepSeek", "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": 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": true, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.0000011, "max_input_tokens": 65536, "max_output_tokens": 8192, "input_cost_per_token_cache_hit": 7e-8, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "deepseek/deepseek-v3", "model_name": "DeepSeek V3", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.27, "output_cost_per_million": 1.1, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": 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_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_response_schema": true, "input_cost_per_token": 9e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://fireworks.ai/pricing", "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/firefunction-v2", "model_name": "Firefunction V2", "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_json_mode": true, "supports_vision": 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": 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 }, { "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_response_schema": 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, "source": "https://fireworks.ai/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": 0, "cache_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": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://fireworks.ai/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": 0.049999999999999996, "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_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": 0.0000025, "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct", "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct", "model_name": "Kimi K2 Instruct", "provider_id": "fireworks", "provider_name": "Fireworks AI", "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_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": 0.0000025, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://app.fireworks.ai/models/fireworks/kimi-k2-instruct-0905", "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct-0905", "model_name": "Kimi K2 Instruct (May 2009)", "provider_id": "fireworks", "provider_name": "Fireworks AI", "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_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": 0.0000025, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://fireworks.ai/pricing", "supports_tool_choice": true, "supports_web_search": true, "model_id": "fireworks_ai/accounts/fireworks/models/kimi-k2-thinking", "model_name": "Kimi K2 Thinking", "provider_id": "fireworks", "provider_name": "Fireworks AI", "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_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": 0.000003, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://fireworks.ai/pricing", "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/kimi-k2p5", "model_name": "Kimi K2p5", "provider_id": "fireworks", "provider_name": "Fireworks 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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000003, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://fireworks.ai/pricing", "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct", "model_name": "Llama V3p1 405B Instruct", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 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_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": 204800, "max_output_tokens": 204800, "max_tokens": 204800, "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/minimax-m2p1", "model_name": "Minimax M2p1", "provider_id": "fireworks", "provider_name": "Fireworks AI", "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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012, "max_input_tokens": 65536, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://fireworks.ai/pricing", "supports_tool_choice": true, "model_id": "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf", "model_name": "Mixtral 8x22B Instruct Hf", "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_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/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_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://fireworks.ai/pricing", "supports_tool_choice": true, "model_id": "fireworks_ai/kimi-k2p5", "model_name": "Kimi K2p5", "provider_id": "fireworks", "provider_name": "Fireworks 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_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": 204800, "max_output_tokens": 204800, "max_tokens": 204800, "source": "https://fireworks.ai/models/fireworks/minimax-m2p1", "supports_tool_choice": true, "model_id": "fireworks_ai/minimax-m2p1", "model_name": "Minimax M2p1", "provider_id": "fireworks", "provider_name": "Fireworks AI", "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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "friendliai/meta-llama-3.1-70b-instruct", "model_name": "Meta Llama 3.1 70B Instruct", "provider_id": "friendliai", "provider_name": "Friendliai", "input_cost_per_million": 0.6, "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": 1e-7, "output_cost_per_token": 1e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "friendliai/meta-llama-3.1-8b-instruct", "model_name": "Meta Llama 3.1 8B Instruct", "provider_id": "friendliai", "provider_name": "Friendliai", "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_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": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-7, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "rpm": 10000, "source": "https://ai.google.dev/pricing#2_0flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_input": true, "supports_audio_output": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 10000000, "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": "2.0-flash", "model_name": "2.0 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "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": 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": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-7, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "rpm": 10000, "source": "https://ai.google.dev/pricing#2_0flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_output": false, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "tpm": 10000000, "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": "2.0-flash-001", "model_name": "2.0 Flash 001", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-8, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 50, "max_video_length": 1, "max_videos_per_prompt": 10, "rpm": 4000, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "tpm": 4000000, "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": "2.0-flash-lite", "model_name": "2.0 Flash Lite", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.075, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 1.875e-8, "cache_read_cost_per_million": 0.01875, "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": 7.5e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-8, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 50, "max_video_length": 1, "max_videos_per_prompt": 10, "rpm": 4000, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "tpm": 4000000, "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": "2.0-flash-lite-001", "model_name": "2.0 Flash Lite 001", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.075, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 1.875e-8, "cache_read_cost_per_million": 0.01875, "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, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 64000, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_images_per_prompt": 3000, "max_tokens": 64000, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/computer-use", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_system_messages": true, "supports_tool_choice": true, "tpm": 800000, "model_id": "2.5-computer-use-preview-10-2025", "model_name": "2.5 Computer Use Preview 10 2025", "provider_id": "google", "provider_name": "Google", "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": 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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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 }, "supports_service_tier": true, "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": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_audio_token": 0.000001, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "supports_reasoning": false, "max_images_per_prompt": 3000, "max_tokens": 32768, "max_pdf_size_mb": 30, "max_video_length": 1, "max_videos_per_prompt": 10, "output_cost_per_image": 0.039, "output_cost_per_image_token": 0.00003, "output_cost_per_reasoning_token": 0.0000025, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": 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 }, "supports_service_tier": true, "model_id": "2.5-flash-image", "model_name": "2.5 Flash Image", "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": "image", "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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 }, "supports_service_tier": true, "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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 }, "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": 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": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 3e-7, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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 }, "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", "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "output_cost_per_reasoning_token": 0.0000025, "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 }, "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": 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_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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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", "supports_service_tier": true, "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 }, "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_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_audio_token": 7e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 10000, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_output": false, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "tpm": 10000000, "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": "2.5-pro-preview-tts", "model_name": "2.5 Pro Preview TTS", "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "output_cost_per_reasoning_token": 0.000003, "rpm": 2000, "source": "https://ai.google.dev/pricing/gemini-3", "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, "supports_service_tier": 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", "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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, "supports_service_tier": 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", "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, "cache_read_input_token_cost_per_audio_token": 5e-8, "input_cost_per_audio_token": 5e-7, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "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_code_execution": true, "supports_file_search": 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": 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", "supports_service_tier": true, "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", "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, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "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, "supports_service_tier": 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", "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, "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "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, "supports_service_tier": 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", "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 1048576, "max_output_tokens": 8192, "input_cost_per_token_above_128k_tokens": 0, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "metadata": { "notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true }, "output_cost_per_token_above_128k_tokens": 0, "rpm": 1000, "source": "https://ai.google.dev/pricing", "supports_system_messages": true, "supports_tool_choice": true, "tpm": 4000000, "model_id": "exp-1114", "model_name": "Exp 1114", "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": 2097152, "max_output_tokens": 8192, "input_cost_per_token_above_128k_tokens": 0, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "metadata": { "notes": "Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true }, "output_cost_per_token_above_128k_tokens": 0, "rpm": 1000, "source": "https://ai.google.dev/pricing", "supports_system_messages": true, "supports_tool_choice": true, "tpm": 4000000, "model_id": "exp-1206", "model_name": "Exp (Jun 2012)", "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_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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "output_cost_per_reasoning_token": 0.0000025, "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 }, "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": 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": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 3e-7, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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 }, "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": 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": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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-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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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 }, "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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 }, "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, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.00000105, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true, "tpm": 250000, "rpm": 10, "model_id": "gemma-2-27b-it", "model_name": "Gemma-2 Instruct (27B)", "provider_id": "google", "provider_name": "Google", "max_input_tokens": 0, "input_cost_per_million": 0.35, "output_cost_per_million": 1.0499999999999998, "cache_read_cost_per_token": 0, "cache_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": 3.5e-7, "output_cost_per_token": 0.00000105, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true, "tpm": 250000, "rpm": 10, "model_id": "gemma-2-9b-it", "model_name": "Gemma-2 Instruct (9B)", "provider_id": "google", "provider_name": "Google", "max_input_tokens": 0, "input_cost_per_million": 0.35, "output_cost_per_million": 1.0499999999999998, "cache_read_cost_per_token": 0, "cache_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, "output_cost_per_token": 0, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, "input_cost_per_character": 0, "input_cost_per_character_above_128k_tokens": 0, "input_cost_per_image": 0, "input_cost_per_image_above_128k_tokens": 0, "input_cost_per_token_above_128k_tokens": 0, "input_cost_per_video_per_second": 0, "input_cost_per_video_per_second_above_128k_tokens": 0, "max_tokens": 8192, "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, "output_cost_per_token_above_128k_tokens": 0, "source": "https://aistudio.google.com", "supports_audio_output": false, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "gemma-3-27b-it", "model_name": "Gemma 3 27B 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": 32767, "max_output_tokens": 8192, "input_cost_per_audio_per_second": 0, "input_cost_per_audio_per_second_above_128k_tokens": 0, "input_cost_per_character": 0, "input_cost_per_character_above_128k_tokens": 0, "input_cost_per_image": 0, "input_cost_per_image_above_128k_tokens": 0, "input_cost_per_token_above_128k_tokens": 0, "input_cost_per_video_per_second": 0, "input_cost_per_video_per_second_above_128k_tokens": 0, "max_tokens": 8192, "output_cost_per_character": 0, "output_cost_per_character_above_128k_tokens": 0, "output_cost_per_token_above_128k_tokens": 0, "source": "https://aistudio.google.com", "supports_audio_output": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "learnlm-1.5-pro-experimental", "model_name": "Learnlm 1.5 Pro Experimental", "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_parallel_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": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000003, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "output_cost_per_audio_token": 0.000012, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_pdf_input": true, "supports_prompt_caching": 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": "live-2.5-flash-preview-native-audio-09-2025", "model_name": "Live 2.5 Flash Preview Native Audio 09 2025", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2, "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": "realtime", "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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 }, "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, "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", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 5e-8, "output_cost_per_token": 8e-8, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "gemma-7b-it", "model_name": "Gemma 7B It", "provider_id": "groq", "provider_name": "Groq", "input_cost_per_million": 0.049999999999999996, "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_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 5e-8, "output_cost_per_token": 8e-8, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "llama-3.1-8b-instant", "model_name": "Llama 3.1 8B Instant", "provider_id": "groq", "provider_name": "Groq", "input_cost_per_million": 0.049999999999999996, "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_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 5.9e-7, "output_cost_per_token": 7.9e-7, "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "model_id": "llama-3.3-70b-versatile", "model_name": "Llama 3.3 70B Versatile", "provider_id": "groq", "provider_name": "Groq", "input_cost_per_million": 0.59, "output_cost_per_million": 0.7899999999999999, "cache_read_cost_per_token": 0, "cache_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_vision": 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": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "meta-llama/llama-4-maverick-17b-128e-instruct", "model_name": "Llama 4 Maverick Instruct (17Bx128E)", "provider_id": "groq", "provider_name": "Groq", "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_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.1e-7, "output_cost_per_token": 3.4e-7, "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "meta-llama/llama-4-scout-17b-16e-instruct", "model_name": "Llama 4 Scout Instruct (17Bx16E)", "provider_id": "groq", "provider_name": "Groq", "input_cost_per_million": 0.11, "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_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "model_id": "moonshotai/kimi-k2-instruct-0905", "model_name": "Kimi K2 Instruct (May 2009)", "provider_id": "groq", "provider_name": "Groq", "input_cost_per_million": 1, "output_cost_per_million": 3, "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_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, "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, "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", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "heroku/claude-3-5-haiku", "model_name": "Claude 3.5 Haiku", "provider_id": "heroku", "provider_name": "Heroku", "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": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "heroku/claude-3-5-sonnet-latest", "model_name": "Claude 3.5 Sonnet", "provider_id": "heroku", "provider_name": "Heroku", "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": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "heroku/claude-3-7-sonnet", "model_name": "Claude 3 7 Sonnet", "provider_id": "heroku", "provider_name": "Heroku", "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": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "heroku/claude-4-sonnet", "model_name": "Claude 4 Sonnet", "provider_id": "heroku", "provider_name": "Heroku", "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, "supports_parallel_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/deepseek-ai/DeepSeek-R1", "model_name": "DeepSeek R1", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "input_cost_per_million": 0.39999999999999997, "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": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 2.5e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/deepseek-ai/DeepSeek-R1-0528", "model_name": "DeepSeek R1 0528", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "input_cost_per_million": 0.25, "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_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": 2e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/deepseek-ai/DeepSeek-V3", "model_name": "DeepSeek V3", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/deepseek-ai/DeepSeek-V3-0324", "model_name": "DeepSeek V3 0324", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "input_cost_per_million": 0.39999999999999997, "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": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/meta-llama/Llama-3.2-3B-Instruct", "model_name": "Llama 3.2 3B Instruct", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "input_cost_per_million": 0.12, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/meta-llama/Llama-3.3-70B-Instruct", "model_name": "Llama 3.3 70B Instruct", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "input_cost_per_million": 0.12, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct", "model_name": "Meta Llama 3 70B Instruct", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "input_cost_per_million": 0.12, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct", "model_name": "Meta Llama 3.1 405B Instruct", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "input_cost_per_million": 0.12, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct", "model_name": "Meta Llama 3.1 70B Instruct", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "input_cost_per_million": 0.12, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct", "model_name": "Meta Llama 3.1 8B Instruct", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "input_cost_per_million": 0.12, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/moonshotai/Kimi-K2-Instruct", "model_name": "Kimi K2 Instruct", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "input_cost_per_million": 2, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B", "model_name": "Hermes 3 Llama 3.1 70B", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "input_cost_per_million": 0.12, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/Qwen/Qwen2.5-72B-Instruct", "model_name": "Qwen2.5 72B Instruct", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "input_cost_per_million": 0.12, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 1.2e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct", "model_name": "Qwen2.5 Coder 32B Instruct", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "input_cost_per_million": 0.12, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/Qwen/Qwen3-235B-A22B", "model_name": "Qwen3 235B A22B", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "input_cost_per_million": 2, "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_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": 2e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "hyperbolic/Qwen/QwQ-32B", "model_name": "QwQ 32B", "provider_id": "hyperbolic", "provider_name": "Hyperbolic", "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_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-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": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/deepseek-v3-0324", "model_name": "Deepseek V3 0324", "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_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/hermes3-405b", "model_name": "Hermes3 405B", "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": 1.2e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/hermes3-70b", "model_name": "Hermes3 70B", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.12, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 2.5e-8, "output_cost_per_token": 4e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/hermes3-8b", "model_name": "Hermes3 8B", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.024999999999999998, "output_cost_per_million": 0.04, "cache_read_cost_per_token": 0, "cache_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": 1e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/lfm-40b", "model_name": "Lfm 40B", "provider_id": "lambda", "provider_name": "Lambda", "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 2.5e-8, "output_cost_per_token": 4e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/lfm-7b", "model_name": "Lfm 7B", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.024999999999999998, "output_cost_per_million": 0.04, "cache_read_cost_per_token": 0, "cache_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": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8", "model_name": "Llama 4 Maverick 17B 128e Instruct 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_parallel_function_calling": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 1e-7, "max_input_tokens": 16384, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/llama-4-scout-17b-16e-instruct", "model_name": "Llama 4 Scout Instruct (17Bx16E)", "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_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_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/llama3.1-405b-instruct-fp8", "model_name": "Llama3.1 405B Instruct Fp8", "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": 1.2e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/llama3.1-70b-instruct-fp8", "model_name": "Llama3.1 70B Instruct Fp8", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.12, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 2.5e-8, "output_cost_per_token": 4e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/llama3.1-8b-instruct", "model_name": "Llama3.1 8B Instruct", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.024999999999999998, "output_cost_per_million": 0.04, "cache_read_cost_per_token": 0, "cache_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": 1.2e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/llama3.1-nemotron-70b-instruct-fp8", "model_name": "Llama3.1 Nemotron 70B Instruct Fp8", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.12, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 1.5e-8, "output_cost_per_token": 2.5e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/llama3.2-11b-vision-instruct", "model_name": "Llama3.2 11B Vision Instruct", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.015, "output_cost_per_million": 0.024999999999999998, "cache_read_cost_per_token": 0, "cache_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, "input_cost_per_token": 1.5e-8, "output_cost_per_token": 2.5e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/llama3.2-3b-instruct", "model_name": "Llama3.2 3B Instruct", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.015, "output_cost_per_million": 0.024999999999999998, "cache_read_cost_per_token": 0, "cache_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": 1.2e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/llama3.3-70b-instruct-fp8", "model_name": "Llama3.3 70B Instruct Fp8", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.12, "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_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_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/qwen25-coder-32b-instruct", "model_name": "Qwen25 Coder 32B Instruct", "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_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_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "lemonade/Gemma-3-4b-it-GGUF", "model_name": "Gemma 3 4B It GGUF", "provider_id": "lemonade", "provider_name": "Lemonade", "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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "model_id": "lemonade/gpt-oss-120b-mxfp-GGUF", "model_name": "GPT Oss 120B Mxfp GGUF", "provider_id": "lemonade", "provider_name": "Lemonade", "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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "model_id": "lemonade/gpt-oss-20b-mxfp4-GGUF", "model_name": "GPT Oss 20B Mxfp4 GGUF", "provider_id": "lemonade", "provider_name": "Lemonade", "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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": 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_tool_choice": true, "model_id": "lemonade/Qwen3-4B-Instruct-2507-GGUF", "model_name": "Qwen3 4B Instruct 2507 GGUF", "provider_id": "lemonade", "provider_name": "Lemonade", "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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": 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_tool_choice": true, "model_id": "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF", "model_name": "Qwen3 Coder 30B A3B Instruct GGUF", "provider_id": "lemonade", "provider_name": "Lemonade", "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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "max_input_tokens": 128000, "max_output_tokens": 4028, "max_tokens": 4028, "source": "https://llama.developer.meta.com/docs/models", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_tool_choice": true, "model_id": "meta_llama/Llama-3.3-70B-Instruct", "model_name": "Llama 3.3 70B Instruct", "provider_id": "meta", "provider_name": "Meta", "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": 128000, "max_output_tokens": 4028, "max_tokens": 4028, "source": "https://llama.developer.meta.com/docs/models", "supported_modalities": [ "text" ], "supported_output_modalities": [ "text" ], "supports_tool_choice": true, "model_id": "meta_llama/Llama-3.3-8B-Instruct", "model_name": "Llama 3.3 8B Instruct", "provider_id": "meta", "provider_name": "Meta", "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": 1000000, "max_output_tokens": 4028, "max_tokens": 4028, "source": "https://llama.developer.meta.com/docs/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_tool_choice": true, "model_id": "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "model_name": "Llama 4 Maverick 17B 128E Instruct FP8", "provider_id": "meta", "provider_name": "Meta", "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": 10000000, "max_output_tokens": 4028, "max_tokens": 4028, "source": "https://llama.developer.meta.com/docs/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_tool_choice": true, "model_id": "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8", "model_name": "Llama 4 Scout 17B 16E Instruct FP8", "provider_id": "meta", "provider_name": "Meta", "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": 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_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "codestral-2405", "model_name": "Codestral (May 2024)", "provider_id": "mistral", "provider_name": "Mistral AI", "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_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": 3e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://mistral.ai/news/codestral-25-08", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "codestral-2508", "model_name": "Codestral (Aug 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "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_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "codestral-latest", "model_name": "Codestral", "provider_id": "mistral", "provider_name": "Mistral AI", "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_json_mode": true, "supports_function_calling": false, "supports_vision": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 2.5e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://mistral.ai/technology/", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "codestral-mamba-latest", "model_name": "Codestral Mamba Latest", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.25, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "source": "https://docs.mistral.ai/capabilities/code_generation/", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "codestral/codestral-2405", "model_name": "Codestral (May 2024)", "provider_id": "mistral", "provider_name": "Mistral AI", "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 }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "source": "https://docs.mistral.ai/capabilities/code_generation/", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "codestral/codestral-latest", "model_name": "Codestral", "provider_id": "mistral", "provider_name": "Mistral AI", "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_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://mistral.ai/news/devstral-2-vibe-cli", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "devstral-2512", "model_name": "Devstral (Dec 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.39999999999999997, "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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://mistral.ai/news/devstral-2-vibe-cli", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "devstral-latest", "model_name": "Devstral Latest", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.39999999999999997, "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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://mistral.ai/news/devstral", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "devstral-medium-2507", "model_name": "Devstral Medium (Jul 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.39999999999999997, "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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://mistral.ai/news/devstral-2-vibe-cli", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "devstral-medium-latest", "model_name": "Devstral Medium Latest", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.39999999999999997, "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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://mistral.ai/news/devstral", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "devstral-small-2505", "model_name": "Devstral Small (May 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "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": 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": 3e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://mistral.ai/news/devstral", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "devstral-small-2507", "model_name": "Devstral Small (Jul 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "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": 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": 3e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "devstral-small-latest", "model_name": "Devstral Small Latest", "provider_id": "mistral", "provider_name": "Mistral AI", "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": 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": 3e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://docs.mistral.ai/models/devstral-small-2-25-12", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "labs-devstral-small-2512", "model_name": "Labs Devstral Small (Dec 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "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": 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, "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", "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, "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", "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, "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", "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, "max_tokens": 40000, "source": "https://mistral.ai/news/magistral", "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": 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", "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": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 40000, "max_output_tokens": 40000, "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", "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": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 40000, "max_output_tokens": 40000, "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", "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": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 40000, "max_output_tokens": 40000, "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-latest", "model_name": "Magistral Small Latest", "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", "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": 2e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "ministral-3-14b-2512", "model_name": "Ministral 3 14B (Dec 2025)", "provider_id": "mistral", "provider_name": "Mistral 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_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": 1e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "ministral-3-3b-2512", "model_name": "Ministral 3 3B (Dec 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "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_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": 1.5e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "ministral-3-8b-2512", "model_name": "Ministral 3 8B (Dec 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "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_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000012, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "mistral-large-2402", "model_name": "Mistral Large (Feb 2024)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 4, "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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000009, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "mistral-large-2407", "model_name": "Mistral Large (Jul 2024)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 3, "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_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": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "mistral-large-2512", "model_name": "Mistral Large (Dec 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", "deprecation_date": 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": 0.0000015, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "mistral-large-3", "model_name": "Mistral Large 3", "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", "deprecation_date": 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": 0.0000015, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "mistral-large-latest", "model_name": "Mistral Large", "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", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_response_schema": true, "input_cost_per_token": 0.0000027, "output_cost_per_token": 0.0000081, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "mistral-medium", "model_name": "Mistral Medium", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 2.7, "output_cost_per_million": 8.1, "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_json_mode": true, "supports_function_calling": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_response_schema": true, "input_cost_per_token": 0.0000027, "output_cost_per_token": 0.0000081, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "mistral-medium-2312", "model_name": "Mistral Medium (Dec 2023)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 2.7, "output_cost_per_million": 8.1, "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_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": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 131072, "max_output_tokens": 8191, "max_tokens": 8191, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "mistral-medium-2505", "model_name": "Mistral Medium (May 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.39999999999999997, "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_vision": 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": 0.000002, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://mistral.ai/news/mistral-medium-3", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "mistral-medium-3-1-2508", "model_name": "Mistral Medium 3 1 (Aug 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.39999999999999997, "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": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_assistant_prefill": 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": 0.39999999999999997, "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_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "mistral-small", "model_name": "Mistral Small", "provider_id": "mistral", "provider_name": "Mistral AI", "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": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 6e-8, "output_cost_per_token": 1.8e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "mistral-small-3-2-2506", "model_name": "Mistral Small 3 2 (Jun 2025)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.06, "output_cost_per_million": 0.18, "cache_read_cost_per_token": 0, "cache_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-8, "output_cost_per_token": 1.8e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://mistral.ai/pricing", "supports_assistant_prefill": 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": 0.06, "output_cost_per_million": 0.18, "cache_read_cost_per_token": 0, "cache_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_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 2.5e-7, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "mistral-tiny", "model_name": "Mistral Tiny", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.25, "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_function_calling": false, "supports_vision": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 2.5e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://mistral.ai/technology/", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "open-codestral-mamba", "model_name": "Codestral Mamba", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.25, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 2.5e-7, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "open-mistral-7b", "model_name": "Open Mistral 7B", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.25, "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_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": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://mistral.ai/technology/", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "open-mistral-nemo", "model_name": "Mistral NeMo", "provider_id": "mistral", "provider_name": "Mistral AI", "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_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://mistral.ai/technology/", "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "open-mistral-nemo-2407", "model_name": "Mistral NeMo (Jul 2024)", "provider_id": "mistral", "provider_name": "Mistral AI", "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_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 65336, "max_output_tokens": 8191, "max_tokens": 8191, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "open-mixtral-8x22b", "model_name": "Mixtral 8x22B", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 2, "output_cost_per_million": 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-7, "output_cost_per_token": 7e-7, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "open-mixtral-8x7b", "model_name": "Open Mixtral 8x7B", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 0.7, "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", "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": 1.5e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "pixtral-12b-2409", "model_name": "Pixtral 12B (Sep 2024)", "provider_id": "mistral", "provider_name": "Mistral AI", "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_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": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "pixtral-large-2411", "model_name": "Pixtral Large (Nov 2024)", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 2, "output_cost_per_million": 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": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "pixtral-large-latest", "model_name": "Pixtral Large", "provider_id": "mistral", "provider_name": "Mistral AI", "input_cost_per_million": 2, "output_cost_per_million": 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, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "supports_tool_choice": true, "supports_web_search": true, "model_id": "moonshot/kimi-k2-0711-preview", "model_name": "Kimi K2 0711 Preview", "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", "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, "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "supports_tool_choice": true, "supports_web_search": true, "model_id": "moonshot/kimi-k2-0905-preview", "model_name": "Kimi K2 0905 Preview", "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", "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, "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", "deprecation_date": null, "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, "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", "deprecation_date": null, "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, "max_tokens": 262144, "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "supports_tool_choice": true, "supports_web_search": true, "model_id": "moonshot/kimi-k2-turbo-preview", "model_name": "Kimi K2 Turbo Preview", "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", "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-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": 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, "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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://platform.moonshot.ai/docs/pricing", "supports_tool_choice": true, "model_id": "moonshot/kimi-latest", "model_name": "Kimi Latest", "provider_id": "moonshot", "provider_name": "Moonshot AI", "input_cost_per_million": 2, "output_cost_per_million": 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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://platform.moonshot.ai/docs/pricing", "supports_tool_choice": true, "model_id": "moonshot/kimi-latest-128k", "model_name": "Kimi Latest 128k", "provider_id": "moonshot", "provider_name": "Moonshot AI", "input_cost_per_million": 2, "output_cost_per_million": 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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://platform.moonshot.ai/docs/pricing", "supports_tool_choice": true, "model_id": "moonshot/kimi-latest-32k", "model_name": "Kimi Latest 32k", "provider_id": "moonshot", "provider_name": "Moonshot AI", "input_cost_per_million": 1, "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_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://platform.moonshot.ai/docs/pricing", "supports_tool_choice": true, "model_id": "moonshot/kimi-latest-8k", "model_name": "Kimi Latest 8k", "provider_id": "moonshot", "provider_name": "Moonshot AI", "input_cost_per_million": 0.19999999999999998, "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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://platform.moonshot.ai/docs/pricing", "supports_tool_choice": true, "model_id": "moonshot/moonshot-v1-128k", "model_name": "Moonshot V1 128k", "provider_id": "moonshot", "provider_name": "Moonshot 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", "deprecation_date": null, "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": 0.000005, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://platform.moonshot.ai/docs/pricing", "supports_tool_choice": true, "model_id": "moonshot/moonshot-v1-128k-0430", "model_name": "Moonshot V1 128k 0430", "provider_id": "moonshot", "provider_name": "Moonshot 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", "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": 0.000002, "output_cost_per_token": 0.000005, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://platform.moonshot.ai/docs/pricing", "supports_tool_choice": true, "model_id": "moonshot/moonshot-v1-128k-vision-preview", "model_name": "Moonshot V1 128k Vision Preview", "provider_id": "moonshot", "provider_name": "Moonshot 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", "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": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://platform.moonshot.ai/docs/pricing", "supports_tool_choice": true, "model_id": "moonshot/moonshot-v1-32k", "model_name": "Moonshot V1 32k", "provider_id": "moonshot", "provider_name": "Moonshot AI", "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": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://platform.moonshot.ai/docs/pricing", "supports_tool_choice": true, "model_id": "moonshot/moonshot-v1-32k-0430", "model_name": "Moonshot V1 32k 0430", "provider_id": "moonshot", "provider_name": "Moonshot AI", "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, "supports_vision": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://platform.moonshot.ai/docs/pricing", "supports_tool_choice": true, "model_id": "moonshot/moonshot-v1-32k-vision-preview", "model_name": "Moonshot V1 32k Vision Preview", "provider_id": "moonshot", "provider_name": "Moonshot AI", "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_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://platform.moonshot.ai/docs/pricing", "supports_tool_choice": true, "model_id": "moonshot/moonshot-v1-8k", "model_name": "Moonshot V1 8k", "provider_id": "moonshot", "provider_name": "Moonshot AI", "input_cost_per_million": 0.19999999999999998, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://platform.moonshot.ai/docs/pricing", "supports_tool_choice": true, "model_id": "moonshot/moonshot-v1-8k-0430", "model_name": "Moonshot V1 8k 0430", "provider_id": "moonshot", "provider_name": "Moonshot AI", "input_cost_per_million": 0.19999999999999998, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://platform.moonshot.ai/docs/pricing", "supports_tool_choice": true, "model_id": "moonshot/moonshot-v1-8k-vision-preview", "model_name": "Moonshot V1 8k Vision Preview", "provider_id": "moonshot", "provider_name": "Moonshot AI", "input_cost_per_million": 0.19999999999999998, "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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000005, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://platform.moonshot.ai/docs/pricing", "supports_tool_choice": true, "model_id": "moonshot/moonshot-v1-auto", "model_name": "Moonshot V1 Auto", "provider_id": "moonshot", "provider_name": "Moonshot 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", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 7e-8, "output_cost_per_token": 2.8e-7, "max_input_tokens": 120000, "max_output_tokens": 8000, "max_tokens": 8000, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/baidu/ernie-4.5-21B-a3b", "model_name": "Ernie 4.5 21B A3B", "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_response_schema": true, "input_cost_per_token": 2.8e-7, "output_cost_per_token": 0.0000011, "max_input_tokens": 123000, "max_output_tokens": 12000, "max_tokens": 12000, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/baidu/ernie-4.5-300b-a47b-paddle", "model_name": "Ernie 4.5 300B A47B Paddle", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.28, "output_cost_per_million": 1.1, "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_json_mode": true, "supports_function_calling": false, "supports_vision": 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, "supports_response_schema": true, "input_cost_per_token": 3e-8, "output_cost_per_token": 3e-8, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/deepseek/deepseek-ocr", "model_name": "Deepseek Ocr", "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_json_mode": true, "supports_function_calling": 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 }, { "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, "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_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": 2.7e-7, "output_cost_per_token": 0.00000112, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_tool_choice": true, "supports_system_messages": true, "input_cost_per_token_cache_hit": 1.35e-7, "model_id": "novita/deepseek/deepseek-v3-0324", "model_name": "Deepseek V3 0324", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.27, "output_cost_per_million": 1.12, "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, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000013, "max_input_tokens": 64000, "max_output_tokens": 16000, "max_tokens": 16000, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/deepseek/deepseek-v3-turbo", "model_name": "Deepseek V3 Turbo", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.3, "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, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 1e-7, "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/google/gemma-3-12b-it", "model_name": "Gemma 3 12B It", "provider_id": "novita", "provider_name": "Novita", "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_json_mode": true, "supports_function_calling": 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": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "supports_system_messages": true, "input_cost_per_token_cache_hit": 6e-8, "model_id": "novita/kwaipilot/kat-coder-pro", "model_name": "Kat Coder Pro", "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": true, "supports_vision": false }, { "supports_response_schema": true, "input_cost_per_token": 5.1e-7, "output_cost_per_token": 7.4e-7, "max_input_tokens": 8192, "max_output_tokens": 8000, "max_tokens": 8000, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/meta-llama/llama-3-70b-instruct", "model_name": "Llama 3 70B Instruct", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.51, "output_cost_per_million": 0.74, "cache_read_cost_per_token": 0, "cache_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-8, "output_cost_per_token": 5e-8, "max_input_tokens": 32768, "max_output_tokens": 32000, "max_tokens": 32000, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/meta-llama/llama-3.2-3b-instruct", "model_name": "Llama 3.2 3B Instruct", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.03, "output_cost_per_million": 0.049999999999999996, "cache_read_cost_per_token": 0, "cache_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": 1.35e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 131072, "max_output_tokens": 120000, "max_tokens": 120000, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/meta-llama/llama-3.3-70b-instruct", "model_name": "Llama 3.3 70B Instruct", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.135, "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": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": 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_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": 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, "model_id": "novita/minimax/minimax-m2.1", "model_name": "Minimax M2.1", "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_parallel_function_calling": 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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_response_schema": true, "input_cost_per_token": 4e-8, "output_cost_per_token": 1.7e-7, "max_input_tokens": 60288, "max_output_tokens": 16000, "max_tokens": 16000, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/mistralai/mistral-nemo", "model_name": "Mistral Nemo", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.04, "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_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": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/moonshotai/kimi-k2-0905", "model_name": "Kimi K2 (May 2009)", "provider_id": "novita", "provider_name": "Novita", "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_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": 5.7e-7, "output_cost_per_token": 0.0000023, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/moonshotai/kimi-k2-instruct", "model_name": "Kimi K2 Instruct", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.5700000000000001, "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_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": 262144, "max_tokens": 262144, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": 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": 0, "cache_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": 1.4e-7, "output_cost_per_token": 1.4e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/nousresearch/hermes-2-pro-llama-3-8b", "model_name": "Hermes 2 Pro Llama 3 8B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.14, "output_cost_per_million": 0.14, "cache_read_cost_per_token": 0, "cache_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_vision": true, "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": true, "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_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 3.8e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 32000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/qwen/qwen-2.5-72b-instruct", "model_name": "Qwen 2.5 72B Instruct", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.38, "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_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": 7e-8, "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/qwen/qwen2.5-7b-instruct", "model_name": "Qwen2.5 7B Instruct", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.07, "output_cost_per_million": 0.07, "cache_read_cost_per_token": 0, "cache_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": 9e-8, "output_cost_per_token": 5.8e-7, "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/qwen/qwen3-235b-a22b-instruct-2507", "model_name": "Qwen3 235B A22B Instruct (Jul 2025)", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.09, "output_cost_per_million": 0.58, "cache_read_cost_per_token": 0, "cache_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, "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, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 7e-8, "output_cost_per_token": 2.7e-7, "max_input_tokens": 160000, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/qwen/qwen3-coder-30b-a3b-instruct", "model_name": "Qwen3 Coder 30B A3B Instruct", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.07, "output_cost_per_million": 0.27, "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", "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-7, "output_cost_per_token": 0.0000013, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/qwen/qwen3-coder-480b-a35b-instruct", "model_name": "Qwen3 Coder 480B A35B Instruct", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.3, "output_cost_per_million": 1.3, "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_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.00000211, "output_cost_per_token": 0.00000845, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/qwen/qwen3-max", "model_name": "Qwen3 Max", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 2.1100000000000003, "output_cost_per_million": 8.450000000000001, "cache_read_cost_per_token": 0, "cache_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, "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_audio_input": true, "supports_audio_output": true, "model_id": "novita/qwen/qwen3-omni-30b-a3b-instruct", "model_name": "Qwen3 Omni 30B A3B Instruct", "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_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_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-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, "model_id": "novita/qwen/qwen3-vl-235b-a22b-instruct", "model_name": "Qwen3 Vl 235B A22B Instruct", "provider_id": "novita", "provider_name": "Novita", "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_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": 7e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/qwen/qwen3-vl-30b-a3b-instruct", "model_name": "Qwen3 Vl 30B A3B Instruct", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.19999999999999998, "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", "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": 0.000001, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/qwen/qwen3-vl-30b-a3b-thinking", "model_name": "Qwen3 Vl 30B A3B Thinking", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.19999999999999998, "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_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": 8e-8, "output_cost_per_token": 5e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/qwen/qwen3-vl-8b-instruct", "model_name": "Qwen3 Vl 8B Instruct", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.08, "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": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.00000148, "output_cost_per_token": 0.00000148, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/sao10k/l3-70b-euryale-v2.1", "model_name": "L3 70B Euryale V2.1", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 1.48, "output_cost_per_million": 1.48, "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": true, "supports_vision": false, "supports_json_mode": false }, { "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 5e-8, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/sao10k/l3-8b-lunaris", "model_name": "L3 8B Lunaris", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.049999999999999996, "cache_read_cost_per_token": 0, "cache_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": 5e-8, "output_cost_per_token": 5e-8, "max_input_tokens": 8192, "max_output_tokens": 32000, "max_tokens": 32000, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/Sao10K/L3-8B-Stheno-v3.2", "model_name": "L3 8B Stheno V3.2", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.049999999999999996, "cache_read_cost_per_token": 0, "cache_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": 0.00000148, "output_cost_per_token": 0.00000148, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/sao10k/l31-70b-euryale-v2.2", "model_name": "L31 70B Euryale V2.2", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 1.48, "output_cost_per_million": 1.48, "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": true, "supports_vision": false, "supports_json_mode": false }, { "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "supports_tool_choice": true, "supports_system_messages": true, "model_id": "novita/skywork/r1v4-lite", "model_name": "R1v4 Lite", "provider_id": "novita", "provider_name": "Novita", "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_json_mode": true, "supports_function_calling": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 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": 2e-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": 0.09999999999999999, "output_cost_per_million": 0.3, "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_vision": 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, "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": 0, "cache_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, "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_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "chatgpt-4o-latest", "model_name": "ChatGPT-4o", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 5, "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_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": 0.0000015, "output_cost_per_token": 0.000006, "max_input_tokens": 200000, "max_output_tokens": 100000, "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", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000006, "max_input_tokens": 16385, "max_output_tokens": 4096, "input_cost_per_token_batches": 0.0000015, "max_tokens": 4096, "output_cost_per_token_batches": 0.000003, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ft:gpt-3.5-turbo", "model_name": "GPT 3.5T [Fine-tuned]", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 3, "output_cost_per_million": 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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000006, "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ft:gpt-3.5-turbo-0125", "model_name": "GPT-3.5 Turbo 0125 [Fine-tuned]", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 3, "output_cost_per_million": 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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000006, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ft:gpt-3.5-turbo-0613", "model_name": "GPT-3.5 Turbo 0613 [Fine-tuned]", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 3, "output_cost_per_million": 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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000006, "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ft:gpt-3.5-turbo-1106", "model_name": "GPT 3.5T (Jun 2011) [Fine-tuned]", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 3, "output_cost_per_million": 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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006, "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ft:gpt-4-0613", "model_name": "GPT-4 0613 [Fine-tuned]", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "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_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": 0.000003, "output_cost_per_token": 0.000012, "max_input_tokens": 1047576, "max_output_tokens": 32768, "input_cost_per_token_batches": 0.0000015, "max_tokens": 32768, "output_cost_per_token_batches": 0.000006, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ft:gpt-4.1-2025-04-14", "model_name": "GPT-4.1 (Apr 2025) [Fine-tuned]", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 3, "output_cost_per_million": 12, "cache_read_cost_per_token": 7.5e-7, "cache_read_cost_per_million": 0.75, "cache_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": 8e-7, "output_cost_per_token": 0.0000032, "max_input_tokens": 1047576, "max_output_tokens": 32768, "input_cost_per_token_batches": 4e-7, "max_tokens": 32768, "output_cost_per_token_batches": 0.0000016, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ft:gpt-4.1-mini-2025-04-14", "model_name": "GPT-4.1 mini (Apr 2025) [Fine-tuned]", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.7999999999999999, "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_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": 2e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 1047576, "max_output_tokens": 32768, "input_cost_per_token_batches": 1e-7, "max_tokens": 32768, "output_cost_per_token_batches": 4e-7, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ft:gpt-4.1-nano-2025-04-14", "model_name": "GPT-4.1 nano (Apr 2025) [Fine-tuned]", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.7999999999999999, "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_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000375, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token_batches": 0.000001875, "max_tokens": 16384, "output_cost_per_token_batches": 0.0000075, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ft:gpt-4o-2024-08-06", "model_name": "GPT-4o (Aug 2024) [Fine-tuned]", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 3.75, "output_cost_per_million": 15, "cache_read_cost_per_token": 0.000001875, "cache_read_cost_per_million": 1.875, "cache_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": 0.00000375, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ft:gpt-4o-2024-11-20", "model_name": "GPT-4o (Nov 2024) [Fine-tuned]", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 3.75, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0.000001875, "cache_write_cost_per_million": 1.875, "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-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token_batches": 1.5e-7, "max_tokens": 16384, "output_cost_per_token_batches": 6e-7, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "ft:gpt-4o-mini-2024-07-18", "model_name": "GPT-4o mini (Jul 2024) [Fine-tuned]", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "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_vision": false }, { "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, "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", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false, "supports_vision": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-3.5-turbo", "model_name": "GPT 3.5T", "provider_id": "openai", "provider_name": "OpenAI", "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, "supports_parallel_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-3.5-turbo-0125", "model_name": "GPT-3.5 Turbo 0125", "provider_id": "openai", "provider_name": "OpenAI", "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000002, "max_input_tokens": 16385, "max_output_tokens": 4096, "deprecation_date": "2026-09-28", "max_tokens": 4096, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-3.5-turbo-1106", "model_name": "GPT 3.5T (Jun 2011)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1, "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", "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000004, "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-3.5-turbo-16k", "model_name": "GPT 3.5T 16k", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 3, "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": 0.00003, "output_cost_per_token": 0.00006, "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4", "model_name": "GPT-4", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "deprecation_date": "2026-03-26", "max_tokens": 4096, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4-0125-preview", "model_name": "GPT-4 0125 Preview", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_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 }, { "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006, "max_input_tokens": 8192, "max_output_tokens": 4096, "deprecation_date": "2026-03-26", "max_tokens": 4096, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4-0314", "model_name": "GPT-4 0314", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "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", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006, "max_input_tokens": 8192, "max_output_tokens": 4096, "deprecation_date": "2025-06-06", "max_tokens": 4096, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4-0613", "model_name": "GPT-4 0613", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "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", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "deprecation_date": "2026-03-26", "max_tokens": 4096, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4-1106-preview", "model_name": "GPT-4 1106 Preview", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_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_vision": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4-turbo", "model_name": "GPT-4 Turbo", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_per_token": 0, "cache_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, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4-turbo-2024-04-09", "model_name": "GPT-4 Turbo (Apr 2024)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_per_token": 0, "cache_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, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4-turbo-preview", "model_name": "GPT-4 Turbo Preview", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_per_token": 0, "cache_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, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 1047576, "max_output_tokens": 32768, "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_priority": 0.0000035, "max_tokens": 32768, "output_cost_per_token_batches": 0.000004, "output_cost_per_token_priority": 0.000014, "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_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_web_search": true, "model_id": "gpt-4.1", "model_name": "GPT-4.1", "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": 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": 1047576, "max_output_tokens": 32768, "input_cost_per_token_batches": 0.000001, "max_tokens": 32768, "output_cost_per_token_batches": 0.000004, "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_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_web_search": true, "model_id": "gpt-4.1-2025-04-14", "model_name": "GPT-4.1 (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", "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": 4e-7, "output_cost_per_token": 0.0000016, "max_input_tokens": 1047576, "max_output_tokens": 32768, "cache_read_input_token_cost_priority": 1.75e-7, "input_cost_per_token_batches": 2e-7, "input_cost_per_token_priority": 7e-7, "max_tokens": 32768, "output_cost_per_token_batches": 8e-7, "output_cost_per_token_priority": 0.0000028, "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_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_web_search": true, "model_id": "gpt-4.1-mini", "model_name": "GPT-4.1 mini", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "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": true }, { "supports_function_calling": true, "supports_parallel_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": 1047576, "max_output_tokens": 32768, "input_cost_per_token_batches": 2e-7, "max_tokens": 32768, "output_cost_per_token_batches": 8e-7, "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_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "supports_web_search": true, "model_id": "gpt-4.1-mini-2025-04-14", "model_name": "GPT-4.1 mini (Apr 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "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": 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": 1047576, "max_output_tokens": 32768, "cache_read_input_token_cost_priority": 5e-8, "input_cost_per_token_batches": 5e-8, "input_cost_per_token_priority": 2e-7, "max_tokens": 32768, "output_cost_per_token_batches": 2e-7, "output_cost_per_token_priority": 8e-7, "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_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "model_id": "gpt-4.1-nano", "model_name": "GPT-4.1 nano", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "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": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1047576, "max_output_tokens": 32768, "input_cost_per_token_batches": 5e-8, "max_tokens": 32768, "output_cost_per_token_batches": 2e-7, "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_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "model_id": "gpt-4.1-nano-2025-04-14", "model_name": "GPT-4.1 nano (Apr 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "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": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "cache_read_input_token_cost_priority": 0.000002125, "input_cost_per_token_batches": 0.00000125, "input_cost_per_token_priority": 0.00000425, "max_tokens": 16384, "output_cost_per_token_batches": 0.000005, "output_cost_per_token_priority": 0.000017, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "model_id": "gpt-4o", "model_name": "GPT-4o", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "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", "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": 0.000005, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_priority": 0.00000875, "max_tokens": 4096, "output_cost_per_token_batches": 0.0000075, "output_cost_per_token_priority": 0.00002625, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-2024-05-13", "model_name": "GPT-4o (May 2024)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 5, "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_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": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token_batches": 0.00000125, "max_tokens": 16384, "output_cost_per_token_batches": 0.000005, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "model_id": "gpt-4o-2024-08-06", "model_name": "GPT-4o (Aug 2024)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "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", "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": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token_batches": 0.00000125, "max_tokens": 16384, "output_cost_per_token_batches": 0.000005, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "model_id": "gpt-4o-2024-11-20", "model_name": "GPT-4o (Nov 2024)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "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", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00004, "max_tokens": 16384, "output_cost_per_audio_token": 0.00008, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-audio-preview", "model_name": "GPT-4o Audio Preview", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00004, "max_tokens": 16384, "output_cost_per_audio_token": 0.00008, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-audio-preview-2024-12-17", "model_name": "GPT-4o Audio Preview (Dec 2024)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00004, "max_tokens": 16384, "output_cost_per_audio_token": 0.00008, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-audio-preview-2025-06-03", "model_name": "GPT-4o Audio Preview (Jun 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "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_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": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "cache_read_input_token_cost_priority": 1.25e-7, "input_cost_per_token_batches": 7.5e-8, "input_cost_per_token_priority": 2.5e-7, "max_tokens": 16384, "output_cost_per_token_batches": 3e-7, "output_cost_per_token_priority": 0.000001, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "model_id": "gpt-4o-mini", "model_name": "GPT-4o mini", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "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": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token_batches": 7.5e-8, "max_tokens": 16384, "output_cost_per_token_batches": 3e-7, "search_context_cost_per_query": { "search_context_size_high": 0.03, "search_context_size_low": 0.025, "search_context_size_medium": 0.0275 }, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, "model_id": "gpt-4o-mini-2024-07-18", "model_name": "GPT-4o mini (Jul 2024)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "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, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00001, "max_tokens": 16384, "output_cost_per_audio_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-mini-audio-preview", "model_name": "GPT-4o Mini Audio Preview", "provider_id": "openai", "provider_name": "OpenAI", "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00001, "max_tokens": 16384, "output_cost_per_audio_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-mini-audio-preview-2024-12-17", "model_name": "GPT-4o Mini Audio Preview (Dec 2024)", "provider_id": "openai", "provider_name": "OpenAI", "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-mini-realtime-preview", "model_name": "GPT-4o Mini Realtime Preview", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-mini-realtime-preview-2024-12-17", "model_name": "GPT-4o Mini Realtime Preview (Dec 2024)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "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_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": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token_batches": 7.5e-8, "max_tokens": 16384, "output_cost_per_token_batches": 3e-7, "search_context_cost_per_query": { "search_context_size_high": 0.03, "search_context_size_low": 0.025, "search_context_size_medium": 0.0275 }, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "gpt-4o-mini-search-preview", "model_name": "GPT-4o Mini Search Preview", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "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": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token_batches": 7.5e-8, "max_tokens": 16384, "output_cost_per_token_batches": 3e-7, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-mini-search-preview-2025-03-11", "model_name": "GPT-4o Mini Search Preview (Mar 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "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, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00002, "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_audio_token": 0.00004, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-realtime-preview", "model_name": "GPT-4o Realtime Preview", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 5, "output_cost_per_million": 20, "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": "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": 0.000005, "output_cost_per_token": 0.00002, "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_audio_token": 0.00004, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-realtime-preview-2024-12-17", "model_name": "GPT-4o Realtime Preview (Dec 2024)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 5, "output_cost_per_million": 20, "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": "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": 0.000005, "output_cost_per_token": 0.00002, "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_audio_token": 0.00004, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-realtime-preview-2025-06-03", "model_name": "GPT-4o Realtime Preview (Jun 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 5, "output_cost_per_million": 20, "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": "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": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token_batches": 0.00000125, "max_tokens": 16384, "output_cost_per_token_batches": 0.000005, "search_context_cost_per_query": { "search_context_size_high": 0.05, "search_context_size_low": 0.03, "search_context_size_medium": 0.035 }, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "gpt-4o-search-preview", "model_name": "GPT-4o Search Preview", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "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", "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": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token_batches": 0.00000125, "max_tokens": 16384, "output_cost_per_token_batches": 0.000005, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-search-preview-2025-03-11", "model_name": "GPT-4o Search Preview (Mar 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "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", "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_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, "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_service_tier": 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, "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, "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_service_tier": 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", "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, "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, "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", "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, "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, "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_service_tier": 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, "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, "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_service_tier": 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", "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, "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, "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, "cache_read_input_token_cost_flex": 2.5e-9, "input_cost_per_token_flex": 2.5e-8, "max_tokens": 128000, "output_cost_per_token_flex": 2e-7, "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", "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": 128000, "max_output_tokens": 272000, "input_cost_per_token_batches": 0.0000075, "max_tokens": 272000, "output_cost_per_token_batches": 0.00006, "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": 128000, "max_output_tokens": 272000, "input_cost_per_token_batches": 0.0000075, "max_tokens": 272000, "output_cost_per_token_batches": 0.00006, "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", "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, "max_tokens": 128000, "supports_pdf_input": true, "supports_prompt_caching": 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-search-api", "model_name": "GPT-5 Search API", "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, "max_tokens": 128000, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "model_id": "gpt-5-search-api-2025-10-14", "model_name": "GPT-5 Search API (Oct 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": 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, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "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, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "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": 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, "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", "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, "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, "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", "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, "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, "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", "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, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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, "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, "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", "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, "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", "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, "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, "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, "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, "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", "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, "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, "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_service_tier": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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, "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_service_tier": true, "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_batches": 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, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "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_batches": 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, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "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, "cache_read_input_token_cost_batches": 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, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "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, "cache_read_input_token_cost_batches": 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, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "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, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "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, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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": 0.000003, "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, "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, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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": 0.000003, "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": 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": 0.000001, "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": 0.00001, "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": 0.00006, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "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": 0.000001, "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": 0.00001, "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": 0.00006, "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_service_tier": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "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, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "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, "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_service_tier": 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": 0.000003, "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, "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, "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_service_tier": 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": 0.000003, "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": false, "supports_response_schema": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.000032, "max_tokens": 16384, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-audio", "model_name": "GPT Audio", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "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": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.000032, "max_tokens": 16384, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-audio-1.5", "model_name": "GPT Audio 1.5", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "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": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.000032, "max_tokens": 16384, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-audio-2025-08-28", "model_name": "GPT Audio (Aug 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "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": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00001, "max_tokens": 16384, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-audio-mini", "model_name": "GPT Audio Mini", "provider_id": "openai", "provider_name": "OpenAI", "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_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00001, "max_tokens": 16384, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-audio-mini-2025-10-06", "model_name": "GPT Audio Mini (Oct 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00001, "max_tokens": 16384, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-audio-mini-2025-12-15", "model_name": "GPT Audio Mini (Dec 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 4096, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime", "model_name": "GPT Realtime", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 16, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "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": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 4096, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime-1.5", "model_name": "GPT Realtime 1.5", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 16, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "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": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 4096, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime-2", "model_name": "GPT Realtime 2", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 16, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "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": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 4096, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime-2025-08-28", "model_name": "GPT Realtime (Aug 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 16, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "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": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime-mini", "model_name": "GPT Realtime Mini", "provider_id": "openai", "provider_name": "OpenAI", "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_image": 8e-7, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime-mini-2025-10-06", "model_name": "GPT Realtime Mini (Oct 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_image": 8e-7, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime-mini-2025-12-15", "model_name": "GPT Realtime Mini (Dec 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "max_input_tokens": 200000, "max_output_tokens": 100000, "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", "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": 0.000015, "output_cost_per_token": 0.00006, "max_input_tokens": 200000, "max_output_tokens": 100000, "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", "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": 0.00015, "output_cost_per_token": 0.0006, "max_input_tokens": 200000, "max_output_tokens": 100000, "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", "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": 0.00015, "output_cost_per_token": 0.0006, "max_input_tokens": 200000, "max_output_tokens": 100000, "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", "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": 0.000002, "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, "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_service_tier": 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, "max_tokens": 100000, "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_service_tier": 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", "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": 0.00001, "output_cost_per_token": 0.00004, "max_input_tokens": 200000, "max_output_tokens": 100000, "input_cost_per_token_batches": 0.000005, "max_tokens": 100000, "output_cost_per_token_batches": 0.00002, "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_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", "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": 0.00004, "max_input_tokens": 200000, "max_output_tokens": 100000, "input_cost_per_token_batches": 0.000005, "max_tokens": 100000, "output_cost_per_token_batches": 0.00002, "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_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", "deprecation_date": null, "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, "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", "deprecation_date": null, "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, "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", "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, "input_cost_per_token_batches": 0.00001, "max_tokens": 100000, "output_cost_per_token_batches": 0.00004, "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, "input_cost_per_token_batches": 0.00001, "max_tokens": 100000, "output_cost_per_token_batches": 0.00004, "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", "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": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "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, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_service_tier": 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", "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": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_service_tier": 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", "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": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 200000, "max_output_tokens": 100000, "input_cost_per_token_batches": 0.000001, "max_tokens": 100000, "output_cost_per_token_batches": 0.000004, "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_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", "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": 0.000008, "max_input_tokens": 200000, "max_output_tokens": 100000, "input_cost_per_token_batches": 0.000001, "max_tokens": 100000, "output_cost_per_token_batches": 0.000004, "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_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", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 200000, "max_output_tokens": 4096, "input_cost_per_image": 0.0004, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "openrouter/anthropic/claude-3-haiku", "model_name": "Claude 3 Haiku", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_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": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 159, "model_id": "openrouter/anthropic/claude-3.5-sonnet", "model_name": "Claude 3.5 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, "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, "tool_use_system_prompt_tokens": 159, "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, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 346, "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, "tool_use_system_prompt_tokens": 159, "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, "tool_use_system_prompt_tokens": 159, "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": 32000, "max_tokens": 32000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_minimal_reasoning_effort": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 159, "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, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "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, "tool_use_system_prompt_tokens": 346, "supports_minimal_reasoning_effort": true, "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": 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, "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, "tool_use_system_prompt_tokens": 346, "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, "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, "tool_use_system_prompt_tokens": 159, "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": 1000000, "max_output_tokens": 1000000, "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": 1000000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 159, "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, "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, "tool_use_system_prompt_tokens": 159, "supports_minimal_reasoning_effort": true, "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 }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 131072, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b", "supports_tool_choice": true, "model_id": "openrouter/bytedance/ui-tars-1.5-7b", "model_name": "Ui Tars 1.5 7B", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "openrouter/deepseek/deepseek-chat", "model_name": "Deepseek Chat", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "openrouter/deepseek/deepseek-chat-v3-0324", "model_name": "Deepseek Chat V3 0324", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_function_calling": false, "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": 8e-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, "model_id": "openrouter/deepseek/deepseek-chat-v3.1", "model_name": "Deepseek Chat V3.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.19999999999999998, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.00000219, "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": 0.55, "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": 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": 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": "openrouter/deepseek/deepseek-v3.2", "model_name": "Deepseek V3.2", "provider_id": "openrouter", "provider_name": "OpenRouter", "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, "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-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": false, "supports_tool_choice": true, "model_id": "openrouter/deepseek/deepseek-v3.2-exp", "model_name": "Deepseek V3.2 Exp", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.19999999999999998, "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, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-7, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "openrouter/google/gemini-2.0-flash-001", "model_name": "Gemini 2.0 Flash 001", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "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", "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": 8192, "input_cost_per_audio_token": 7e-7, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "openrouter/google/gemini-2.5-flash", "model_name": "Gemini 2.5 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 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": 8192, "input_cost_per_audio_token": 7e-7, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "openrouter/google/gemini-2.5-pro", "model_name": "Gemini 2.5 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "output_cost_per_reasoning_token": 0.000003, "rpm": 2000, "source": "https://ai.google.dev/pricing/gemini-3", "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": 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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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": 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, "cache_read_input_token_cost_per_audio_token": 5e-8, "input_cost_per_audio_token": 5e-7, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "output_cost_per_reasoning_token": 0.0000015, "rpm": 2000, "source": "https://ai.google.dev/pricing/gemini-3", "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_code_execution": true, "supports_file_search": 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, "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 }, { "input_cost_per_token": 0.000001875, "output_cost_per_token": 0.000001875, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "openrouter/gryphe/mythomax-l2-13b", "model_name": "MythoMax-L2 (13B)", "provider_id": "openrouter", "provider_name": "OpenRouter", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.875, "output_cost_per_million": 1.875, "cache_read_cost_per_token": 0, "cache_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": 0.000005625, "output_cost_per_token": 0.000005625, "max_input_tokens": 8000, "max_output_tokens": 2000, "max_tokens": 2000, "supports_tool_choice": true, "model_id": "openrouter/mancer/weaver", "model_name": "Weaver", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 5.625, "output_cost_per_million": 5.625, "cache_read_cost_per_token": 0, "cache_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": 5.9e-7, "output_cost_per_token": 7.9e-7, "max_input_tokens": 8192, "max_output_tokens": 8000, "max_tokens": 8000, "supports_tool_choice": true, "model_id": "openrouter/meta-llama/llama-3-70b-instruct", "model_name": "Llama 3 70B Instruct", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.59, "output_cost_per_million": 0.7899999999999999, "cache_read_cost_per_token": 0, "cache_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": 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": 2.7e-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": 0.27, "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": false, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000011, "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": 0.3, "output_cost_per_million": 1.1, "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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 262144, "max_output_tokens": 65536, "input_cost_per_image": 0, "max_tokens": 65536, "supports_prompt_caching": false, "supports_tool_choice": true, "model_id": "openrouter/mistralai/devstral-2512", "model_name": "Devstral (Dec 2025)", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_image": 0, "max_tokens": 262144, "supports_prompt_caching": false, "supports_tool_choice": true, "model_id": "openrouter/mistralai/ministral-14b-2512", "model_name": "Ministral 14B (Dec 2025)", "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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_image": 0, "max_tokens": 131072, "supports_prompt_caching": false, "supports_tool_choice": true, "model_id": "openrouter/mistralai/ministral-3b-2512", "model_name": "Ministral 3B (Dec 2025)", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_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": 1.5e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_image": 0, "max_tokens": 262144, "supports_prompt_caching": false, "supports_tool_choice": true, "model_id": "openrouter/mistralai/ministral-8b-2512", "model_name": "Ministral 8B (Dec 2025)", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 1.3e-7, "max_input_tokens": 32768, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "openrouter/mistralai/mistral-7b-instruct", "model_name": "Mistral 7B Instruct", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.13, "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": 0.000008, "output_cost_per_token": 0.000024, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "openrouter/mistralai/mistral-large", "model_name": "Mistral Large", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 8, "output_cost_per_million": 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_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": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_image": 0, "max_tokens": 262144, "supports_prompt_caching": false, "supports_tool_choice": true, "model_id": "openrouter/mistralai/mistral-large-2512", "model_name": "Mistral Large (Dec 2025)", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "openrouter/mistralai/mistral-small-3.1-24b-instruct", "model_name": "Mistral Small 3.1 24B Instruct", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "openrouter/mistralai/mistral-small-3.2-24b-instruct", "model_name": "Mistral Small 3.2 24B Instruct", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 6.5e-7, "max_input_tokens": 65536, "max_output_tokens": 65536, "max_tokens": 65536, "supports_tool_choice": true, "model_id": "openrouter/mistralai/mixtral-8x22b-instruct", "model_name": "Mixtral 8x22B Instruct", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.65, "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_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": 6e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://openrouter.ai/moonshotai/kimi-k2.5", "supports_tool_choice": true, "supports_video_input": true, "model_id": "openrouter/moonshotai/kimi-k2.5", "model_name": "Kimi K2.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002, "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-3.5-turbo", "model_name": "GPT 3.5T", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.5, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000004, "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-3.5-turbo-16k", "model_name": "GPT 3.5T 16k", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 3, "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 }, { "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006, "max_input_tokens": 8191, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-4", "model_name": "GPT-4", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 30, "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 }, { "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": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-4.1", "model_name": "GPT-4.1", "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": true }, { "supports_function_calling": true, "supports_parallel_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": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-4.1-mini", "model_name": "GPT-4.1 mini", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "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": 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": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-4.1-nano", "model_name": "GPT-4.1 nano", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "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, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-4o", "model_name": "GPT-4o", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2.5, "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_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-4o-2024-05-13", "model_name": "GPT-4o (May 2024)", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 5, "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_parallel_functions": true, "supports_json_mode": 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, "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, "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 }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_image": 0, "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "openrouter/openai/gpt-5.2-chat", "model_name": "GPT-5.2 Chat", "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_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 8e-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": 0.18, "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_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-8, "output_cost_per_token": 1e-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": 0.02, "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": 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": 0.000015, "output_cost_per_token": 0.00006, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "openrouter/openai/o1", "model_name": "o1", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_json_mode": true, "supports_parallel_functions": true }, { "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_reasoning": true, "supports_tool_choice": true, "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": 0, "cache_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": 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_reasoning": true, "supports_tool_choice": true, "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": 0, "cache_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_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 }, { "input_cost_per_token": 1.8e-7, "output_cost_per_token": 1.8e-7, "max_input_tokens": 33792, "max_output_tokens": 33792, "max_tokens": 33792, "supports_tool_choice": true, "model_id": "openrouter/qwen/qwen-2.5-coder-32b-instruct", "model_name": "Qwen 2.5 Coder 32B Instruct", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.18, "output_cost_per_million": 0.18, "cache_read_cost_per_token": 0, "cache_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": 2.1e-7, "output_cost_per_token": 6.3e-7, "max_input_tokens": 8192, "max_output_tokens": 2048, "max_tokens": 2048, "supports_tool_choice": true, "model_id": "openrouter/qwen/qwen-vl-plus", "model_name": "Qwen Vl Plus", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.21, "output_cost_per_million": 0.63, "cache_read_cost_per_token": 0, "cache_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, "input_cost_per_token": 7.1e-8, "output_cost_per_token": 1e-7, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507", "supports_tool_choice": true, "model_id": "openrouter/qwen/qwen3-235b-a22b-2507", "model_name": "Qwen3 235B A22B (Jul 2025)", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.071, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.1e-7, "output_cost_per_token": 6e-7, "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": 0.11, "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": 2.2e-7, "output_cost_per_token": 9.5e-7, "max_input_tokens": 262100, "max_output_tokens": 262100, "max_tokens": 262100, "source": "https://openrouter.ai/qwen/qwen3-coder", "supports_tool_choice": true, "model_id": "openrouter/qwen/qwen3-coder", "model_name": "Qwen3 Coder", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.22, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "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": 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_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": 0.000002, "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": 0.39999999999999997, "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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": 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://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": 0.3, "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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": 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://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": 0.25, "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": 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": 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": 0.6, "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": 1e-7, "output_cost_per_token": 4e-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": 0.09999999999999999, "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": 4e-7, "output_cost_per_token": 0.0000024, "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": 0.39999999999999997, "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": false, "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 }, { "input_cost_per_token": 8.5e-7, "output_cost_per_token": 0.0000034, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://openrouter.ai/switchpoint/router", "supports_tool_choice": true, "model_id": "openrouter/switchpoint/router", "model_name": "Router", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.85, "output_cost_per_million": 3.4, "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": 0.000001875, "output_cost_per_token": 0.000001875, "max_input_tokens": 6144, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "openrouter/undi95/remm-slerp-l2-13b", "model_name": "Remm Slerp L2 13B", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.875, "output_cost_per_million": 1.875, "cache_read_cost_per_token": 0, "cache_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": 0.000015, "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": false, "input_cost_per_token": 9e-8, "output_cost_per_token": 2.9e-7, "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": false, "model_id": "openrouter/xiaomi/mimo-v2-flash", "model_name": "Mimo V2 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09, "output_cost_per_million": 0.29, "cache_read_cost_per_token": 0, "cache_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": 4e-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": 0.39999999999999997, "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_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, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000015, "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": 1.5, "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": 7e-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": 0.07, "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_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.00000256, "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": 0.7999999999999999, "output_cost_per_million": 2.56, "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_vision": false, "supports_json_mode": false, "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://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b", "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": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "max_input_tokens": 131000, "max_output_tokens": 131000, "max_tokens": 131000, "source": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct", "supports_tool_choice": true, "model_id": "ovhcloud/Llama-3.1-8B-Instruct", "model_name": "Llama 3.1 8B Instruct", "provider_id": "ovhcloud", "provider_name": "Ovhcloud", "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_json_mode": true, "supports_vision": false, "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://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct", "supports_tool_choice": true, "model_id": "ovhcloud/Meta-Llama-3_3-70B-Instruct", "model_name": "Meta Llama 3_3 70B Instruct", "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": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 1e-7, "max_input_tokens": 127000, "max_output_tokens": 127000, "max_tokens": 127000, "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3", "supports_tool_choice": true, "model_id": "ovhcloud/Mistral-7B-Instruct-v0.3", "model_name": "Mistral 7B Instruct V0.3", "provider_id": "ovhcloud", "provider_name": "Ovhcloud", "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_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 1.3e-7, "max_input_tokens": 118000, "max_output_tokens": 118000, "max_tokens": 118000, "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407", "supports_tool_choice": true, "model_id": "ovhcloud/Mistral-Nemo-Instruct-2407", "model_name": "Mistral Nemo Instruct (Jul 2024)", "provider_id": "ovhcloud", "provider_name": "Ovhcloud", "input_cost_per_million": 0.13, "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_vision": false, "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": 2.8e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506", "supports_tool_choice": true, "model_id": "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506", "model_name": "Mistral Small 3.2 24B Instruct (Jun 2025)", "provider_id": "ovhcloud", "provider_name": "Ovhcloud", "input_cost_per_million": 0.09, "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_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://endpoints.ai.cloud.ovh.net/models/qwen3-32b", "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, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://platform.publicai.co/docs", "supports_tool_choice": true, "model_id": "publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT", "model_name": "Gemma SEA LION V4 27B IT", "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, "model_id": "publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT", "model_name": "Qwen SEA LION V4 32B IT", "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-3-32B-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, "model_id": "publicai/allenai/Olmo-3-7B-Instruct", "model_name": "Olmo 3 7B Instruct", "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, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://platform.publicai.co/docs", "supports_tool_choice": true, "model_id": "publicai/BSC-LT/ALIA-40b-instruct_Q8_0", "model_name": "ALIA 40B Instruct_Q8_0", "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": 16384, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://platform.publicai.co/docs", "supports_tool_choice": true, "model_id": "publicai/BSC-LT/salamandra-7b-instruct-tools-16k", "model_name": "Salamandra 7B Instruct Tools 16k", "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_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "supports_system_messages": true, "supports_tool_choice": true, "supports_prompt_caching": true, "model_id": "anthropic/claude-3.5-haiku", "model_name": "Claude 3.5 Haiku", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "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": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000375, "output_cost_per_token": 0.00001875, "supports_system_messages": true, "supports_tool_choice": true, "supports_prompt_caching": true, "model_id": "anthropic/claude-3.5-sonnet", "model_name": "Claude 3.5 Sonnet", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 3.75, "output_cost_per_million": 18.75, "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_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": 0.000015, "supports_system_messages": true, "supports_tool_choice": true, "supports_prompt_caching": true, "model_id": "anthropic/claude-3.7-sonnet", "model_name": "Claude 3.7 Sonnet", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "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": 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": 0.000015, "supports_system_messages": true, "supports_tool_choice": true, "supports_prompt_caching": true, "model_id": "anthropic/claude-4-sonnet", "model_name": "Claude 4 Sonnet", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "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": 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, "supports_system_messages": true, "supports_tool_choice": true, "supports_prompt_caching": true, "model_id": "anthropic/claude-4.5-haiku", "model_name": "Claude 4.5 Haiku", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "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": 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": 0.000015, "supports_system_messages": true, "supports_tool_choice": true, "supports_prompt_caching": true, "model_id": "anthropic/claude-4.5-sonnet", "model_name": "Claude 4.5 Sonnet", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "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": 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": 0.0000025, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "google/gemini-2.5-flash", "model_name": "Gemini 2.5 Flash", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "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_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, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "google/gemini-3-pro", "model_name": "Gemini 3 Pro", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "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": true }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "meta/llama-2-13b", "model_name": "Llama 2 13B", "provider_id": "replicate", "provider_name": "Replicate", "input_cost_per_million": 0.09999999999999999, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "meta/llama-2-13b-chat", "model_name": "Llama 2 13B Chat", "provider_id": "replicate", "provider_name": "Replicate", "input_cost_per_million": 0.09999999999999999, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 0.00000275, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "meta/llama-2-70b", "model_name": "Llama 2 70B", "provider_id": "replicate", "provider_name": "Replicate", "input_cost_per_million": 0.65, "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", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 0.00000275, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "meta/llama-2-70b-chat", "model_name": "LLaMA 2 70b Chat", "provider_id": "replicate", "provider_name": "Replicate", "input_cost_per_million": 0.65, "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", "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": 2.5e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "meta/llama-2-7b", "model_name": "Llama 2 7B", "provider_id": "replicate", "provider_name": "Replicate", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5e-8, "output_cost_per_token": 2.5e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "meta/llama-2-7b-chat", "model_name": "Llama 2 7B Chat", "provider_id": "replicate", "provider_name": "Replicate", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 0.00000275, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "meta/llama-3-70b", "model_name": "Llama 3 70B", "provider_id": "replicate", "provider_name": "Replicate", "input_cost_per_million": 0.65, "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", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6.5e-7, "output_cost_per_token": 0.00000275, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "meta/llama-3-70b-instruct", "model_name": "Llama 3 70B Instruct", "provider_id": "replicate", "provider_name": "Replicate", "input_cost_per_million": 0.65, "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", "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": 2.5e-7, "max_input_tokens": 8086, "max_output_tokens": 8086, "max_tokens": 8086, "supports_tool_choice": true, "model_id": "meta/llama-3-8b", "model_name": "Llama 3 8B", "provider_id": "replicate", "provider_name": "Replicate", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5e-8, "output_cost_per_token": 2.5e-7, "max_input_tokens": 8086, "max_output_tokens": 8086, "max_tokens": 8086, "supports_tool_choice": true, "model_id": "meta/llama-3-8b-instruct", "model_name": "Llama 3 8B Instruct", "provider_id": "replicate", "provider_name": "Replicate", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5e-8, "output_cost_per_token": 2.5e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "mistralai/mistral-7b-instruct-v0.2", "model_name": "Mistral 7B Instruct V0.2", "provider_id": "replicate", "provider_name": "Replicate", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5e-8, "output_cost_per_token": 2.5e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "mistralai/mistral-7b-v0.1", "model_name": "Mistral 7B V0.1", "provider_id": "replicate", "provider_name": "Replicate", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "mistralai/mixtral-8x7b-instruct-v0.1", "model_name": "Mixtral 8x7B Instruct V0.1", "provider_id": "replicate", "provider_name": "Replicate", "input_cost_per_million": 0.3, "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, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "openai/gpt-4.1", "model_name": "GPT-4.1", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "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_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": 4e-7, "output_cost_per_token": 0.0000016, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "openai/gpt-4.1-mini", "model_name": "GPT-4.1 mini", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "cache_read_cost_per_token": 0, "cache_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": 0.0000025, "output_cost_per_token": 0.00001, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": true, "supports_audio_output": true, "model_id": "openai/gpt-4o", "model_name": "GPT-4o", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2.5, "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": 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": 6e-7, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "openai/gpt-4o-mini", "model_name": "GPT-4o mini", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "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_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, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "openai/gpt-5", "model_name": "GPT-5", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "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": 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, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "openai/gpt-5-mini", "model_name": "GPT-5 Mini", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "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": true }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.0000045, "max_input_tokens": 32768, "max_output_tokens": 32768, "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", "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": 0.0000045, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "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": 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/gpt-oss-120b", "model_name": "GPT Oss 120B", "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, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 6.3e-7, "output_cost_per_token": 0.0000018, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "metadata": { "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" }, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_tool_choice": true, "model_id": "sambanova/Llama-4-Maverick-17B-128E-Instruct", "model_name": "Llama 4 Maverick 17B 128E Instruct", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.63, "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_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 7e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "metadata": { "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" }, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_tool_choice": true, "model_id": "sambanova/Llama-4-Scout-17B-16E-Instruct", "model_name": "Llama 4 Scout 17B 16E Instruct", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.39999999999999997, "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", "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": 0.000005, "output_cost_per_token": 0.00001, "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_tool_choice": true, "model_id": "sambanova/Meta-Llama-3.1-405B-Instruct", "model_name": "Meta Llama 3.1 405B Instruct", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 5, "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_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": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_tool_choice": true, "model_id": "sambanova/Meta-Llama-3.1-8B-Instruct", "model_name": "Meta Llama 3.1 8B Instruct", "provider_id": "sambanova", "provider_name": "Sambanova", "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": 6e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_tool_choice": true, "model_id": "sambanova/Meta-Llama-3.3-70B-Instruct", "model_name": "Meta Llama 3.3 70B Instruct", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.6, "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, "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://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": 0.3, "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": 4e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "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", "deprecation_date": null, "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": 0.000003, "output_cost_per_token": 0.000007, "max_input_tokens": 128000, "max_output_tokens": 20480, "max_tokens": 20480, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-R1", "model_name": "DeepSeek R1", "provider_id": "together", "provider_name": "Together AI", "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_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": 5.5e-7, "output_cost_per_token": 0.00000219, "max_input_tokens": 128000, "source": "https://www.together.ai/models/deepseek-r1-0528-throughput", "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-R1-0528-tput", "model_name": "DeepSeek R1 0528 Tput", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "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_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00000125, "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "deepseek-ai/DeepSeek-V3", "model_name": "DeepSeek V3", "provider_id": "together", "provider_name": "Together AI", "input_cost_per_million": 1.25, "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_json_mode": true, "supports_parallel_functions": true, "supports_vision": 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, "max_tokens": 16384, "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", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "model_id": "meta-llama/Llama-3.2-3B-Instruct-Turbo", "model_name": "Llama 3.2 3B Instruct Turbo", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 8.8e-7, "output_cost_per_token": 8.8e-7, "supports_tool_choice": true, "model_id": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "model_name": "Llama 3.3 70B Instruct Turbo", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.88, "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_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "supports_tool_choice": true, "model_id": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free", "model_name": "Llama 3.3 70B Instruct Turbo Free", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "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": 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": 8.5e-7, "supports_tool_choice": true, "model_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "model_name": "Llama 4 Maverick 17B 128E Instruct FP8", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.27, "output_cost_per_million": 0.85, "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_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": 1.8e-7, "output_cost_per_token": 5.9e-7, "supports_tool_choice": true, "model_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "model_name": "Llama 4 Scout 17B 16E Instruct", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.18, "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_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": 0.0000035, "output_cost_per_token": 0.0000035, "supports_tool_choice": true, "model_id": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", "model_name": "Meta Llama 3.1 405B Instruct Turbo", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 3.5, "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": 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": 8.8e-7, "output_cost_per_token": 8.8e-7, "supports_tool_choice": true, "model_id": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "model_name": "Meta Llama 3.1 70B Instruct Turbo", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.88, "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_parallel_functions": true, "supports_vision": 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": 1.8e-7, "supports_tool_choice": true, "model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "model_name": "Meta Llama 3.1 8B Instruct Turbo", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.18, "output_cost_per_million": 0.18, "cache_read_cost_per_token": 0, "cache_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, "supports_tool_choice": true, "model_id": "mistralai/Mistral-7B-Instruct-v0.1", "model_name": "Mistral 7B Instruct V0.1", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "model_id": "mistralai/Mistral-Small-24B-Instruct-2501", "model_name": "Mistral Small 24B Instruct (Jan 2025)", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "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_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": 6e-7, "supports_tool_choice": true, "model_id": "mistralai/Mixtral-8x7B-Instruct-v0.1", "model_name": "Mixtral 8x7B Instruct V0.1", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.6, "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": 0.000001, "output_cost_per_token": 0.000003, "source": "https://www.together.ai/models/kimi-k2-instruct", "supports_tool_choice": true, "model_id": "moonshotai/Kimi-K2-Instruct", "model_name": "Kimi K2 Instruct", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "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_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "source": "https://www.together.ai/models/kimi-k2-0905", "supports_tool_choice": true, "model_id": "moonshotai/Kimi-K2-Instruct-0905", "model_name": "Kimi K2 Instruct (May 2009)", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000028, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://www.together.ai/models/kimi-k2-5", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "moonshotai/Kimi-K2.5", "model_name": "Kimi K2.5", "provider_id": "together", "provider_name": "Together AI", "input_cost_per_million": 0.5, "output_cost_per_million": 2.8, "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_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": 6e-7, "max_input_tokens": 131072, "max_output_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", "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": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 128000, "source": "https://www.together.ai/models/gpt-oss-20b", "supports_tool_choice": true, "model_id": "openai/gpt-oss-20b", "model_name": "GPT Oss 20B", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "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_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "model_id": "Qwen/Qwen2.5-72B-Instruct-Turbo", "model_name": "Qwen2.5 72B Instruct Turbo", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "model_id": "Qwen/Qwen2.5-7B-Instruct-Turbo", "model_name": "Qwen2.5 7B Instruct Turbo", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.000006, "max_input_tokens": 262000, "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8", "supports_tool_choice": true, "model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507-tput", "model_name": "Qwen3 235B A22B Instruct 2507 Tput", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 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": 6.5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 256000, "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507", "supports_tool_choice": true, "model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507", "model_name": "Qwen3 235B A22B Thinking (Jul 2025)", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.65, "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": true, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002, "max_input_tokens": 256000, "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct", "supports_tool_choice": true, "model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "model_name": "Qwen3 Coder 480B A35B Instruct FP8", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 2, "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": 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": 262144, "source": "https://www.together.ai/models/qwen3-next-80b-a3b-instruct", "supports_tool_choice": true, "model_id": "Qwen/Qwen3-Next-80B-A3B-Instruct", "model_name": "Qwen3 Next 80B A3B Instruct", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "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": 262144, "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking", "supports_tool_choice": true, "model_id": "Qwen/Qwen3-Next-80B-A3B-Thinking", "model_name": "Qwen3 Next 80B A3B Thinking", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "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": 6e-7, "output_cost_per_token": 0.0000036, "max_input_tokens": 262144, "source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B", "supports_tool_choice": true, "model_id": "Qwen/Qwen3.5-397B-A17B", "model_name": "Qwen3.5 397B A17B", "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": 0, "cache_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_tool_choice": true, "model_id": "togethercomputer/CodeLlama-34b-Instruct", "model_name": "CodeLlama 34B Instruct", "provider_id": "together", "provider_name": "Together AI", "max_input_tokens": 0, "max_output_tokens": 0, "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_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": 2e-7, "output_cost_per_token": 0.0000011, "max_input_tokens": 128000, "source": "https://www.together.ai/models/glm-4-5-air", "supports_tool_choice": true, "model_id": "zai-org/GLM-4.5-Air-FP8", "model_name": "GLM 4.5 Air FP8", "provider_id": "together", "provider_name": "Together AI", "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.1, "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_json_mode": true, "supports_parallel_functions": true, "supports_vision": 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": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "source": "https://www.together.ai/models/glm-4-6", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "zai-org/GLM-4.6", "model_name": "GLM 4.6", "provider_id": "together", "provider_name": "Together 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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 4.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "source": "https://www.together.ai/models/glm-4-7", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "zai-org/GLM-4.7", "model_name": "GLM 4.7", "provider_id": "together", "provider_name": "Together AI", "input_cost_per_million": 0.44999999999999996, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "v0/v0-1.0-md", "model_name": "V0 1.0 Md", "provider_id": "v0", "provider_name": "V0", "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_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": 0.000075, "max_input_tokens": 512000, "max_output_tokens": 512000, "max_tokens": 512000, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "v0/v0-1.5-lg", "model_name": "V0 1.5 Lg", "provider_id": "v0", "provider_name": "V0", "input_cost_per_million": 15, "output_cost_per_million": 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_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "v0/v0-1.5-md", "model_name": "V0 1.5 Md", "provider_id": "v0", "provider_name": "V0", "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_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 40960, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/alibaba/qwen-3-32b", "model_name": "Qwen 3 32B", "provider_id": "vercel", "provider_name": "Vercel", "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": 4e-7, "output_cost_per_token": 0.0000016, "max_input_tokens": 262144, "max_output_tokens": 66536, "max_tokens": 66536, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/alibaba/qwen3-coder", "model_name": "Qwen3 Coder", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "cache_read_cost_per_token": 0, "cache_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": 0.000003, "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_prompt_caching": true, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/anthropic/claude-3-5-sonnet", "model_name": "Claude 3.5 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": 0.000003, "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_prompt_caching": true, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/anthropic/claude-3-5-sonnet-20241022", "model_name": "Claude 3.5 Sonnet (Oct 2024)", "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": 0.000003, "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": 2.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/anthropic/claude-3-haiku", "model_name": "Claude 3 Haiku", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.25, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 3e-7, "cache_write_cost_per_million": 0.3, "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": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/anthropic/claude-3-opus", "model_name": "Claude 3 Opus", "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": 8e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/anthropic/claude-3.5-haiku", "model_name": "Claude 3.5 Haiku", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 4, "cache_read_cost_per_token": 8e-8, "cache_read_cost_per_million": 0.08, "cache_write_cost_per_token": 0.000001, "cache_write_cost_per_million": 1, "model_type": "chat", "deprecation_date": 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_tool_choice": true, "model_id": "vercel_ai_gateway/anthropic/claude-3.5-sonnet", "model_name": "Claude 3.5 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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "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": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "max_tokens": 32000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/anthropic/claude-4-opus", "model_name": "Claude 4 Opus", "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, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/anthropic/claude-4-sonnet", "model_name": "Claude 4 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_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": 0.000001, "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, "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, "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, "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_minimal_reasoning_effort": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "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, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_minimal_reasoning_effort": true, "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, "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, "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_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 256000, "max_output_tokens": 8000, "max_tokens": 8000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/cohere/command-a", "model_name": "Command A", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 2.5, "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_vision": 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": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/cohere/command-r", "model_name": "Command R", "provider_id": "vercel", "provider_name": "Vercel", "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": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/cohere/command-r-plus", "model_name": "Command R+", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 2.5, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.00000219, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/deepseek/deepseek-r1", "model_name": "DeepSeek R1", "provider_id": "vercel", "provider_name": "Vercel", "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_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": 7.5e-7, "output_cost_per_token": 9.9e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b", "model_name": "Deepseek R1 Distill Llama 70B", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.75, "output_cost_per_million": 0.9900000000000001, "cache_read_cost_per_token": 0, "cache_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": 9e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/deepseek/deepseek-v3", "model_name": "DeepSeek V3", "provider_id": "vercel", "provider_name": "Vercel", "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 }, { "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": 8192, "deprecation_date": "2026-06-01", "max_tokens": 8192, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/google/gemini-2.0-flash", "model_name": "Gemini 2.0 Flash", "provider_id": "vercel", "provider_name": "Vercel", "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", "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-8, "output_cost_per_token": 3e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "max_tokens": 8192, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/google/gemini-2.0-flash-lite", "model_name": "Gemini 2.0 Flash-Lite", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.075, "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", "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": 65536, "max_tokens": 65536, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/google/gemini-2.5-flash", "model_name": "Gemini 2.5 Flash", "provider_id": "vercel", "provider_name": "Vercel", "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/google/gemini-2.5-pro", "model_name": "Gemini 2.5 Pro", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 2.5, "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, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/google/gemma-2-9b", "model_name": "Gemma 2 9B", "provider_id": "vercel", "provider_name": "Vercel", "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": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5.9e-7, "output_cost_per_token": 7.9e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/meta/llama-3-70b", "model_name": "Llama 3 70B", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.59, "output_cost_per_million": 0.7899999999999999, "cache_read_cost_per_token": 0, "cache_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": 5e-8, "output_cost_per_token": 8e-8, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/meta/llama-3-8b", "model_name": "Llama 3 8B", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.049999999999999996, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/meta/llama-3.1-70b", "model_name": "Llama 3.1 70B", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.72, "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_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": 1.6e-7, "output_cost_per_token": 1.6e-7, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/meta/llama-3.2-11b", "model_name": "Llama 3.2 11B", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.16, "output_cost_per_million": 0.16, "cache_read_cost_per_token": 0, "cache_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": 7.2e-7, "output_cost_per_token": 7.2e-7, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/meta/llama-3.2-90b", "model_name": "Llama 3.2 90B", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.72, "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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/meta/llama-3.3-70b", "model_name": "Llama 3.3 70B", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.72, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/meta/llama-4-maverick", "model_name": "Llama 4 Maverick", "provider_id": "vercel", "provider_name": "Vercel", "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_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": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/meta/llama-4-scout", "model_name": "Llama 4 Scout", "provider_id": "vercel", "provider_name": "Vercel", "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 }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 256000, "max_output_tokens": 4000, "max_tokens": 4000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/mistral/codestral", "model_name": "Codestral", "provider_id": "vercel", "provider_name": "Vercel", "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, "supports_response_schema": true, "input_cost_per_token": 7e-8, "output_cost_per_token": 2.8e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/mistral/devstral-small", "model_name": "Devstral Small", "provider_id": "vercel", "provider_name": "Vercel", "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": 0.000002, "output_cost_per_token": 0.000005, "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/mistral/magistral-medium", "model_name": "Magistral Medium", "provider_id": "vercel", "provider_name": "Vercel", "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", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-8, "output_cost_per_token": 4e-8, "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/mistral/ministral-3b", "model_name": "Ministral 3B", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.04, "output_cost_per_million": 0.04, "cache_read_cost_per_token": 0, "cache_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": 1e-7, "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/mistral/ministral-8b", "model_name": "Ministral 8B", "provider_id": "vercel", "provider_name": "Vercel", "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_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 32000, "max_output_tokens": 4000, "max_tokens": 4000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/mistral/mistral-large", "model_name": "Mistral Large", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 2, "output_cost_per_million": 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, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 32000, "max_output_tokens": 4000, "max_tokens": 4000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/mistral/mistral-small", "model_name": "Mistral Small", "provider_id": "vercel", "provider_name": "Vercel", "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": 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": 1.5e-7, "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/mistral/pixtral-12b", "model_name": "Pixtral 12B", "provider_id": "vercel", "provider_name": "Vercel", "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_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": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/mistral/pixtral-large", "model_name": "Pixtral Large", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 2, "output_cost_per_million": 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, "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/moonshotai/kimi-k2", "model_name": "Kimi K2", "provider_id": "vercel", "provider_name": "Vercel", "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_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": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/openai/gpt-3.5-turbo", "model_name": "GPT 3.5T", "provider_id": "vercel", "provider_name": "Vercel", "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, "supports_vision": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/openai/gpt-4-turbo", "model_name": "GPT-4 Turbo", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_per_token": 0, "cache_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": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/openai/gpt-4.1", "model_name": "GPT-4.1", "provider_id": "vercel", "provider_name": "Vercel", "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/openai/gpt-4.1-mini", "model_name": "GPT-4.1 mini", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "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": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/openai/gpt-4.1-nano", "model_name": "GPT-4.1 nano", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/openai/gpt-4o", "model_name": "GPT-4o", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "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", "deprecation_date": 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": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/openai/gpt-4o-mini", "model_name": "GPT-4o mini", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "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": 0.000015, "output_cost_per_token": 0.00006, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/openai/o1", "model_name": "o1", "provider_id": "vercel", "provider_name": "Vercel", "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_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, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/openai/o3", "model_name": "o3", "provider_id": "vercel", "provider_name": "Vercel", "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_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, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/openai/o3-mini", "model_name": "o3 mini", "provider_id": "vercel", "provider_name": "Vercel", "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_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": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/openai/o4-mini", "model_name": "o4 mini", "provider_id": "vercel", "provider_name": "Vercel", "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, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 32000, "max_tokens": 32000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/vercel/v0-1.0-md", "model_name": "V0 1.0 Md", "provider_id": "vercel", "provider_name": "Vercel", "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, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/vercel/v0-1.5-md", "model_name": "V0 1.5 Md", "provider_id": "vercel", "provider_name": "Vercel", "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": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 131072, "max_output_tokens": 4000, "max_tokens": 4000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/xai/grok-2", "model_name": "Grok 2", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 2, "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_vision": false, "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": 0.00001, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/xai/grok-2-vision", "model_name": "Grok 2 Vision", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 2, "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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/xai/grok-3", "model_name": "Grok 3", "provider_id": "vercel", "provider_name": "Vercel", "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, "input_cost_per_token": 3e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/xai/grok-3-mini", "model_name": "Grok 3 Mini", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.3, "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, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/xai/grok-3-mini-fast", "model_name": "Grok 3 Mini Fast", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.6, "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_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, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/xai/grok-4", "model_name": "Grok 4", "provider_id": "vercel", "provider_name": "Vercel", "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, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/zai/glm-4.5", "model_name": "Glm 4.5", "provider_id": "vercel", "provider_name": "Vercel", "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": 2e-7, "output_cost_per_token": 0.0000011, "max_input_tokens": 128000, "max_output_tokens": 96000, "max_tokens": 96000, "supports_tool_choice": true, "model_id": "vercel_ai_gateway/zai/glm-4.5-air", "model_name": "Glm 4.5 Air", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.1, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 4.5e-7, "output_cost_per_token": 0.0000018, "max_input_tokens": 200000, "max_output_tokens": 200000, "max_tokens": 200000, "source": "https://vercel.com/ai-gateway/models/glm-4.6", "supports_tool_choice": true, "model_id": "vercel_ai_gateway/zai/glm-4.6", "model_name": "Glm 4.6", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.44999999999999996, "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_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "claude-3-5-haiku", "model_name": "Claude 3.5 Haiku", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "claude-3-5-haiku@20241022", "model_name": "Claude 3 5 Haiku@ (Oct 2024)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_vision": false, "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": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "claude-3-5-sonnet", "model_name": "Claude 3.5 Sonnet", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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, "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_pdf_input": true, "supports_tool_choice": true, "model_id": "claude-3-5-sonnet@20240620", "model_name": "Claude 3 5 Sonnet@ (Jun 2024)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 8192, "deprecation_date": "2026-05-11", "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, "tool_use_system_prompt_tokens": 159, "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, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-3-haiku", "model_name": "Claude 3 Haiku", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_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": 0.00000125, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-3-haiku@20240307", "model_name": "Claude 3 Haiku@ (Mar 2024)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_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": 4096, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-3-opus", "model_name": "Claude 3 Opus", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 15, "output_cost_per_million": 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": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-3-opus@20240229", "model_name": "Claude 3 Opus@ (Feb 2024)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 15, "output_cost_per_million": 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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-3-sonnet", "model_name": "Claude 3 Sonnet", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-3-sonnet@20240229", "model_name": "Claude 3 Sonnet@ (Feb 2024)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "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, "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", "deprecation_date": 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": 8192, "max_tokens": 8192, "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, "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", "deprecation_date": 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, "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, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": null, "supports_json_mode": true, "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_token_batches": 0.0000075, "max_tokens": 32000, "output_cost_per_token_batches": 0.0000375, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-opus-4-1", "model_name": "Claude Opus 4 1", "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", "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_token_batches": 0.0000075, "max_tokens": 32000, "output_cost_per_token_batches": 0.0000375, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-opus-4-1@20250805", "model_name": "Claude Opus 4 1@ (Aug 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", "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": 200000, "max_output_tokens": 64000, "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_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": 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, "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_minimal_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "tool_use_system_prompt_tokens": 159, "supports_native_streaming": true, "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", "deprecation_date": 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, "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, "tool_use_system_prompt_tokens": 346, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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", "deprecation_date": 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, "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, "tool_use_system_prompt_tokens": 346, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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", "deprecation_date": 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, "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_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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", "deprecation_date": 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, "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_xhigh_reasoning_effort": true, "tool_use_system_prompt_tokens": 346, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "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", "deprecation_date": 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, "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, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": 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, "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, "tool_use_system_prompt_tokens": 159, "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", "deprecation_date": 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, "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, "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-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", "deprecation_date": 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, "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, "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, "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", "deprecation_date": 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, "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, "tool_use_system_prompt_tokens": 346, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_minimal_reasoning_effort": true, "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, "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, "tool_use_system_prompt_tokens": 346, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_minimal_reasoning_effort": true, "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, "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, "tool_use_system_prompt_tokens": 159, "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", "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": 9e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "codestral-2", "model_name": "Codestral 2", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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": 3e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "codestral-2@001", "model_name": "Codestral 2@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "codestral-2501", "model_name": "Codestral (Jan 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "codestral@2405", "model_name": "Codestral@2405", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "codestral@latest", "model_name": "Codestral@latest", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_vision": false, "supports_json_mode": false, "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": 0.00000135, "output_cost_per_token": 0.0000054, "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": 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": 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": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-7, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "source": "https://ai.google.dev/pricing#2_0flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_input": true, "supports_audio_output": true, "supports_prompt_caching": 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 }, "model_id": "gemini-2.0-flash", "model_name": "Gemini 2.0 Flash", "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": 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": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 0.000001, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 8192, "max_video_length": 1, "max_videos_per_prompt": 10, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_output": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": 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 }, "model_id": "gemini-2.0-flash-001", "model_name": "Gemini 2.0 Flash 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "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", "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-8, "output_cost_per_token": 3e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-8, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 50, "max_video_length": 1, "max_videos_per_prompt": 10, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": 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 }, "model_id": "gemini-2.0-flash-lite", "model_name": "Gemini 2.0 Flash-Lite", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.075, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 1.875e-8, "cache_read_cost_per_million": 0.01875, "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-8, "output_cost_per_token": 3e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-8, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 50, "max_video_length": 1, "max_videos_per_prompt": 10, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": 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 }, "model_id": "gemini-2.0-flash-lite-001", "model_name": "Gemini 2.0 Flash Lite 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.075, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 1.875e-8, "cache_read_cost_per_million": 0.01875, "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, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 64000, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_images_per_prompt": 3000, "max_tokens": 64000, "output_cost_per_token_above_200k_tokens": 0.000015, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gemini-2.5-computer-use-preview-10-2025", "model_name": "Gemini 2.5 Computer Use Preview 10 2025", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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": 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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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 }, "supports_service_tier": true, "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", "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": 32768, "max_output_tokens": 32768, "input_cost_per_audio_token": 0.000001, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_tokens": 32768, "max_pdf_size_mb": 30, "max_video_length": 1, "max_videos_per_prompt": 10, "output_cost_per_image": 0.039, "output_cost_per_image_token": 0.00003, "output_cost_per_reasoning_token": 0.0000025, "rpm": 100000, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/image-generation#edit-an-image", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": false, "tpm": 8000000, "model_id": "gemini-2.5-flash-image", "model_name": "Gemini 2.5 Flash Image", "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": "image", "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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 }, "supports_service_tier": true, "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", "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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 }, "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": 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": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 3e-7, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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 }, "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "output_cost_per_reasoning_token": 0.0000025, "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 }, "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": 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_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, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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 }, "supports_service_tier": true, "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", "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": 0.00000125, "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_audio_token": 7e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "output_cost_per_token_above_200k_tokens": 0.000015, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_output": false, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": 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 }, "model_id": "gemini-2.5-pro-preview-tts", "model_name": "Gemini 2.5 Pro Preview TTS", "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", "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-7, "output_cost_per_token": 0.000003, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "output_cost_per_reasoning_token": 0.000003, "source": "https://ai.google.dev/pricing/gemini-3", "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, "supports_service_tier": 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", "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "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, "supports_service_tier": 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", "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, "cache_read_input_token_cost_per_audio_token": 5e-8, "input_cost_per_audio_token": 5e-7, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "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_code_execution": true, "supports_file_search": 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, "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-3.1-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, "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "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, "supports_service_tier": 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", "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, "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_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65536, "max_video_length": 1, "max_videos_per_prompt": 10, "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, "supports_service_tier": 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", "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": 3e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000003, "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "max_images_per_prompt": 3000, "max_pdf_size_mb": 30, "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, "output_cost_per_audio_token": 0.000012, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/vertex_ai/live" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_pdf_input": true, "supports_prompt_caching": 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 }, "model_id": "gemini-live-2.5-flash-preview-native-audio-09-2025", "model_name": "Gemini Live 2.5 Flash Preview Native Audio 09 2025", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2, "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": "realtime", "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://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": 2e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "jamba-1.5", "model_name": "Jamba 1.5", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.19999999999999998, "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_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": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "jamba-1.5-large", "model_name": "Jamba 1.5 Large", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "jamba-1.5-large@001", "model_name": "Jamba 1.5 Large@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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": 2e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "jamba-1.5-mini", "model_name": "Jamba 1.5 Mini", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.19999999999999998, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "jamba-1.5-mini@001", "model_name": "Jamba 1.5 Mini@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.19999999999999998, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 8192, "max_output_tokens": 1024, "input_cost_per_character": 0.000005, "max_tokens": 1024, "output_cost_per_character": 0.000015, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true, "model_id": "medlm-large", "model_name": "Medlm Large", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_character": 5e-7, "max_tokens": 8192, "output_cost_per_character": 0.000001, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true, "model_id": "medlm-medium", "model_name": "Medlm Medium", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000016, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "model_id": "meta/llama-3.1-405b-instruct-maas", "model_name": "Llama 3.1 405B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 16, "cache_read_cost_per_token": 0, "cache_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, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "model_id": "meta/llama-3.1-70b-instruct-maas", "model_name": "Llama 3.1 70B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." }, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "model_id": "meta/llama-3.1-8b-instruct-maas", "model_name": "Llama 3.1 8B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." }, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "model_id": "meta/llama-3.2-90b-vision-instruct-maas", "model_name": "Llama 3.2 90B Vision Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.00000115, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_tool_choice": true, "model_id": "meta/llama-4-maverick-17b-128e-instruct-maas", "model_name": "Llama 4 Maverick 17B 128e Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.35, "output_cost_per_million": 1.15, "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, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.00000115, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_tool_choice": true, "model_id": "meta/llama-4-maverick-17b-16e-instruct-maas", "model_name": "Llama 4 Maverick 17B 16e Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.35, "output_cost_per_million": 1.15, "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, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 7e-7, "max_input_tokens": 10000000, "max_output_tokens": 10000000, "max_tokens": 10000000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_tool_choice": true, "model_id": "meta/llama-4-scout-17b-128e-instruct-maas", "model_name": "Llama 4 Scout 17B 128e Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "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", "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": 7e-7, "max_input_tokens": 10000000, "max_output_tokens": 10000000, "max_tokens": 10000000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_tool_choice": true, "model_id": "meta/llama-4-scout-17b-16e-instruct-maas", "model_name": "Llama 4 Scout 17B 16e Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "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", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true, "model_id": "meta/llama3-405b-instruct-maas", "model_name": "Llama3 405B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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 }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true, "model_id": "meta/llama3-70b-instruct-maas", "model_name": "Llama3 70B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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 }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true, "model_id": "meta/llama3-8b-instruct-maas", "model_name": "Llama3 8B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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, "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://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true, "model_id": "minimaxai/minimax-m2-maas", "model_name": "Minimax M2 Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral-large-2411", "model_name": "Mistral Large (Nov 2024)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 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": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral-large@2407", "model_name": "Mistral Large@2407", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 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": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral-large@2411-001", "model_name": "Mistral Large@2411 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 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": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral-large@latest", "model_name": "Mistral Large@latest", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 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": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral-medium-3", "model_name": "Mistral Medium 3", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.39999999999999997, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral-medium-3@001", "model_name": "Mistral Medium 3@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.39999999999999997, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000003, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "mistral-nemo@2407", "model_name": "Mistral Nemo@2407", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 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_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": 1.5e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "mistral-nemo@latest", "model_name": "Mistral Nemo@latest", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "mistral-small-2503", "model_name": "Mistral Small (Mar 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_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": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral-small-2503@001", "model_name": "Mistral Small 2503@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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": 3e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "mistralai/codestral-2", "model_name": "Codestral 2", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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": 3e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "mistralai/codestral-2@001", "model_name": "Codestral 2@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistralai/mistral-medium-3", "model_name": "Mistral Medium 3", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.39999999999999997, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistralai/mistral-medium-3@001", "model_name": "Mistral Medium 3@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.39999999999999997, "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_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": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true, "supports_web_search": true, "model_id": "moonshotai/kimi-k2-thinking-maas", "model_name": "Kimi K2 Thinking Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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": 2.5e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global", "us-south1" ], "supports_tool_choice": true, "model_id": "qwen/qwen3-235b-a22b-instruct-2507-maas", "model_name": "Qwen3 235B A22B Instruct 2507 Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global" ], "supports_tool_choice": true, "model_id": "qwen/qwen3-coder-480b-a35b-instruct-maas", "model_name": "Qwen3 Coder 480B A35B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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_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": 262144, "max_tokens": 262144, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global" ], "supports_tool_choice": true, "model_id": "qwen/qwen3-next-80b-a3b-instruct-maas", "model_name": "Qwen3 Next 80B A3B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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": 1.5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global" ], "supports_tool_choice": true, "model_id": "qwen/qwen3-next-80b-a3b-thinking-maas", "model_name": "Qwen3 Next 80B A3B Thinking Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", "supports_tool_choice": true, "supports_web_search": true, "model_id": "xai/grok-4.1-fast-non-reasoning", "model_name": "Grok 4.1 Fast Non 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, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", "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, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", "supports_tool_choice": true, "supports_web_search": true, "model_id": "xai/grok-4.20-non-reasoning", "model_name": "Grok 4.20 Non Reasoning", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "xai/grok-4.20-reasoning", "model_name": "Grok 4.20 Reasoning", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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, "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_parallel_function_calling": false, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "supports_audio_input": false, "supports_audio_output": false, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "watsonx/ibm/granite-3-8b-instruct", "model_name": "Granite 3 8B Instruct", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "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": true, "supports_parallel_function_calling": false, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.00001, "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "supports_audio_input": false, "supports_audio_output": false, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "watsonx/mistralai/mistral-large", "model_name": "Mistral Large", "provider_id": "watsonx", "provider_name": "IBM Watsonx", "input_cost_per_million": 3, "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, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-2", "model_name": "Grok 2", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-2-1212", "model_name": "Grok 2 (Dec 2012)", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-2-latest", "model_name": "Grok 2 Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "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_vision": false, "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": 0.00001, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_image": 0.000002, "max_tokens": 32768, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-2-vision", "model_name": "Grok 2 Vision", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 32768, "max_output_tokens": 32768, "deprecation_date": "2026-02-28", "input_cost_per_image": 0.000002, "max_tokens": 32768, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-2-vision-1212", "model_name": "Grok 2 Vision (Dec 2012)", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "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", "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": 0.00001, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_image": 0.000002, "max_tokens": 32768, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-2-vision-latest", "model_name": "Grok 2 Vision Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-3", "model_name": "Grok 3", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 7.5e-7, "cache_read_cost_per_million": 0.75, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-3-beta", "model_name": "Grok 3 Beta", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 7.5e-7, "cache_read_cost_per_million": 0.75, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-3-fast-beta", "model_name": "Grok 3 Fast Beta", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 5, "output_cost_per_million": 25, "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", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-3-fast-latest", "model_name": "Grok 3 Fast Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 5, "output_cost_per_million": 25, "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", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-3-latest", "model_name": "Grok 3 Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 7.5e-7, "cache_read_cost_per_million": 0.75, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 3e-7, "output_cost_per_token": 5e-7, "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, "model_id": "grok-3-mini", "model_name": "Grok 3 Mini", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 0.3, "output_cost_per_million": 0.5, "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": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 3e-7, "output_cost_per_token": 5e-7, "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, "model_id": "grok-3-mini-beta", "model_name": "Grok 3 Mini Beta", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 0.3, "output_cost_per_million": 0.5, "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": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-3-mini-fast", "model_name": "Grok 3 Mini Fast", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 0.6, "output_cost_per_million": 4, "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": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-3-mini-fast-beta", "model_name": "Grok 3 Mini Fast Beta", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 0.6, "output_cost_per_million": 4, "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": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-3-mini-fast-latest", "model_name": "Grok 3 Mini Fast Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 0.6, "output_cost_per_million": 4, "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": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 3e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://x.ai/api#pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-3-mini-latest", "model_name": "Grok 3 Mini Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 0.3, "output_cost_per_million": 0.5, "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": false, "supports_vision": false, "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://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4", "model_name": "Grok 4", "provider_id": "xai", "provider_name": "xAI", "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, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token_above_128k_tokens": 0.000006, "max_tokens": 256000, "output_cost_per_token_above_128k_tokens": 0.00003, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4-0709", "model_name": "Grok 4 (Sep 2007)", "provider_id": "xai", "provider_name": "xAI", "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": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "input_cost_per_token_above_128k_tokens": 4e-7, "max_tokens": 2000000, "output_cost_per_token_above_128k_tokens": 0.000001, "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, "model_id": "grok-4-1-fast", "model_name": "Grok 4 1 Fast", "provider_id": "xai", "provider_name": "xAI", "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, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "input_cost_per_token_above_128k_tokens": 4e-7, "max_tokens": 2000000, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", "supports_audio_input": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4-1-fast-non-reasoning", "model_name": "Grok 4 1 Fast Non Reasoning", "provider_id": "xai", "provider_name": "xAI", "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, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "input_cost_per_token_above_128k_tokens": 4e-7, "max_tokens": 2000000, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", "supports_audio_input": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4-1-fast-non-reasoning-latest", "model_name": "Grok 4 1 Fast Non Reasoning Latest", "provider_id": "xai", "provider_name": "xAI", "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, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "input_cost_per_token_above_128k_tokens": 4e-7, "max_tokens": 2000000, "output_cost_per_token_above_128k_tokens": 0.000001, "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, "model_id": "grok-4-1-fast-reasoning", "model_name": "Grok 4 1 Fast Reasoning", "provider_id": "xai", "provider_name": "xAI", "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, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "input_cost_per_token_above_128k_tokens": 4e-7, "max_tokens": 2000000, "output_cost_per_token_above_128k_tokens": 0.000001, "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, "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": 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": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "input_cost_per_token_above_128k_tokens": 4e-7, "max_tokens": 2000000, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4-fast-non-reasoning", "model_name": "Grok 4 Fast Non Reasoning", "provider_id": "xai", "provider_name": "xAI", "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "input_cost_per_token_above_128k_tokens": 4e-7, "max_tokens": 2000000, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4-fast-reasoning", "model_name": "Grok 4 Fast Reasoning", "provider_id": "xai", "provider_name": "xAI", "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_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, "max_input_tokens": 256000, "max_output_tokens": 256000, "input_cost_per_token_above_128k_tokens": 0.000006, "max_tokens": 256000, "output_cost_per_token_above_128k_tokens": 0.00003, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4-latest", "model_name": "Grok 4 Latest", "provider_id": "xai", "provider_name": "xAI", "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, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "source": "https://docs.x.ai/docs/models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": 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": 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": 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": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "source": "https://docs.x.ai/docs/models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4.20-beta-0309-non-reasoning", "model_name": "Grok 4.20 Beta 0309 Non Reasoning", "provider_id": "xai", "provider_name": "xAI", "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": 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": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "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-4.20-beta-0309-reasoning", "model_name": "Grok 4.20 Beta 0309 Reasoning", "provider_id": "xai", "provider_name": "xAI", "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": 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": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "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-4.20-multi-agent-beta-0309", "model_name": "Grok 4.20 Multi Agent Beta (Sep 2003)", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 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": 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, "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, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000015, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-beta", "model_name": "Grok Beta", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 5, "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": 2e-7, "output_cost_per_token": 0.0000015, "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, "model_id": "grok-code-fast", "model_name": "Grok Code Fast", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.5, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000015, "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, "model_id": "grok-code-fast-1", "model_name": "Grok Code Fast 1", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.5, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000015, "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, "model_id": "grok-code-fast-1-0825", "model_name": "Grok Code Fast 1 0825", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.5, "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_vision": false, "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": 0.000015, "max_input_tokens": 8192, "max_output_tokens": 8192, "input_cost_per_image": 0.000005, "max_tokens": 8192, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-vision-beta", "model_name": "Grok Vision Beta", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 5, "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": 1e-7, "output_cost_per_token": 1e-7, "max_input_tokens": 128000, "max_output_tokens": 32000, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "model_id": "zai/glm-4-32b-0414-128k", "model_name": "Glm 4 32B 0414 128k", "provider_id": "zai", "provider_name": "Zai", "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_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": 128000, "max_output_tokens": 32000, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "model_id": "zai/glm-4.5", "model_name": "Glm 4.5", "provider_id": "zai", "provider_name": "Zai", "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": 2e-7, "output_cost_per_token": 0.0000011, "max_input_tokens": 128000, "max_output_tokens": 32000, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "model_id": "zai/glm-4.5-air", "model_name": "Glm 4.5 Air", "provider_id": "zai", "provider_name": "Zai", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.1, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000045, "max_input_tokens": 128000, "max_output_tokens": 32000, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "model_id": "zai/glm-4.5-airx", "model_name": "Glm 4.5 Airx", "provider_id": "zai", "provider_name": "Zai", "input_cost_per_million": 1.1, "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": 0, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_output_tokens": 32000, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "model_id": "zai/glm-4.5-flash", "model_name": "Glm 4.5 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": 0.0000022, "output_cost_per_token": 0.0000089, "max_input_tokens": 128000, "max_output_tokens": 32000, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "model_id": "zai/glm-4.5-x", "model_name": "Glm 4.5 X", "provider_id": "zai", "provider_name": "Zai", "input_cost_per_million": 2.2, "output_cost_per_million": 8.9, "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, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000018, "max_input_tokens": 128000, "max_output_tokens": 32000, "supports_tool_choice": true, "source": "https://docs.z.ai/guides/overview/pricing", "model_id": "zai/glm-4.5v", "model_name": "Glm 4.5v", "provider_id": "zai", "provider_name": "Zai", "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_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-4.6", "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": 0.000001, "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 } ]