[ { "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_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, "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": 0.00000125, "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": 0.000002, "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": 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": 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": false, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 16384, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_none_reasoning_effort": true, "model_id": "azure/gpt-5.1-chat-2025-11-13", "model_name": "GPT-5.1 Chat (Nov 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "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": 0.00000175, "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, "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_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, "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": 0.000003, "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 }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 7e-7, "max_input_tokens": 70000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_system_messages": true, "model_id": "ai21.jamba-instruct-v1:0", "model_name": "Jamba Instruct", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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, "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": 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": 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, "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": 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 }, { "supports_vision": true, "input_cost_per_token": 9e-8, "output_cost_per_token": 2.9e-7, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "model_id": "google.gemma-3-12b-it", "model_name": "Google.gemma 3 12B It", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 2.3e-7, "output_cost_per_token": 3.8e-7, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "model_id": "google.gemma-3-27b-it", "model_name": "Google.gemma 3 27B It", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.22999999999999998, "output_cost_per_million": 0.38, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 4e-8, "output_cost_per_token": 8e-8, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "model_id": "google.gemma-3-4b-it", "model_name": "Google.gemma 3 4B It", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.04, "output_cost_per_million": 0.08, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_native_structured_output": true, "model_id": "minimax.minimax-m2", "model_name": "Minimax.minimax M2", "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_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": 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 }, { "supports_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_reasoning": true, "supports_system_messages": true, "model_id": "mistral.magistral-small-2509", "model_name": "Magistral Small (Sep 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.5, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_native_structured_output": true, "model_id": "mistral.ministral-3-14b-instruct", "model_name": "Ministral 3 14B Instruct", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_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": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_native_structured_output": true, "model_id": "mistral.ministral-3-3b-instruct", "model_name": "Ministral 3 3B Instruct", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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": 1.5e-7, "output_cost_per_token": 1.5e-7, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_native_structured_output": true, "model_id": "mistral.ministral-3-8b-instruct", "model_name": "Ministral 3 8B Instruct", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_native_structured_output": true, "model_id": "mistral.mistral-large-3-675b-instruct", "model_name": "Mistral Large 3 675B Instruct", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.5, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 4e-8, "output_cost_per_token": 4e-8, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true, "model_id": "mistral.voxtral-mini-3b-2507", "model_name": "Voxtral Mini 3B (Jul 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_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": 8192, "max_tokens": 8192, "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true, "model_id": "mistral.voxtral-small-24b-2507", "model_name": "Voxtral Small 24B (Jul 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_reasoning": true, "supports_system_messages": true, "supports_native_structured_output": true, "model_id": "moonshot.kimi-k2-thinking", "model_name": "Moonshot.kimi K2 Thinking", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.6, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "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_vision": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "model_id": "nvidia.nemotron-nano-12b-v2", "model_name": "Nvidia.nemotron Nano 12B V2", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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_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 }, { "input_cost_per_token": 6e-8, "output_cost_per_token": 2.3e-7, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "model_id": "nvidia.nemotron-nano-9b-v2", "model_name": "Nvidia.nemotron Nano 9B V2", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.06, "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_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": 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 }, { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "model_id": "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 7e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "model_id": "openai.gpt-oss-safeguard-20b", "model_name": "Openai.GPT Oss Safeguard 20B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.07, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "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": 1.5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_native_structured_output": true, "model_id": "qwen.qwen3-next-80b-a3b", "model_name": "Qwen.qwen3 Next 80B A3B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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": 5.3e-7, "output_cost_per_token": 0.00000266, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "supports_native_structured_output": true, "model_id": "qwen.qwen3-vl-235b-a22b", "model_name": "Qwen.qwen3 Vl 235B A22B", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.53, "output_cost_per_million": 2.66, "cache_read_cost_per_token": 0, "cache_read_cost_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": "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 }, { "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 }, { "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": 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, "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 }, { "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, "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": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000007, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "model_id": "crusoe/deepseek-ai/DeepSeek-R1-0528", "model_name": "DeepSeek R1 0528", "provider_id": "crusoe", "provider_name": "Crusoe", "input_cost_per_million": 3, "output_cost_per_million": 7, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": 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": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.0000025, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "model_id": "crusoe/moonshotai/Kimi-K2-Thinking", "model_name": "Kimi K2 Thinking", "provider_id": "crusoe", "provider_name": "Crusoe", "input_cost_per_million": 2.5, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_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, "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": false, "supports_parallel_function_calling": false, "supports_response_schema": true, "input_cost_per_token": 2.8e-7, "output_cost_per_token": 4.2e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "model_id": "deepseek-reasoner", "model_name": "Deepseek Reasoner", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.28, "output_cost_per_million": 0.42, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_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": false, "supports_parallel_function_calling": false, "supports_response_schema": true, "input_cost_per_token": 2.8e-7, "output_cost_per_token": 4.2e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "input_cost_per_token_cache_hit": 2.8e-8, "max_tokens": 65536, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "model_id": "deepseek/deepseek-reasoner", "model_name": "Deepseek Reasoner", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.28, "output_cost_per_million": 0.42, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false, "supports_vision": false }, { "supports_function_calling": true, "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, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "model_id": "gigachat/GigaChat-2-Lite", "model_name": "GigaChat 2 Lite", "provider_id": "gigachat", "provider_name": "Gigachat", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "model_id": "gigachat/GigaChat-2-Max", "model_name": "GigaChat 2 Max", "provider_id": "gigachat", "provider_name": "Gigachat", "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, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "model_id": "gigachat/GigaChat-2-Pro", "model_name": "GigaChat 2 Pro", "provider_id": "gigachat", "provider_name": "Gigachat", "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": 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, "supports_image_size": false, "model_id": "2.5-flash", "model_name": "2.5 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 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, "supports_image_size": false, "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, "supports_image_size": false, "model_id": "2.5-flash-lite", "model_name": "2.5 Flash Lite", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2025-11-18", "input_cost_per_audio_token": 5e-7, "max_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_image_size": false, "model_id": "2.5-flash-lite-preview-06-17", "model_name": "2.5 Flash Lite Preview 06 17", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 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 }, "supports_image_size": false, "model_id": "2.5-flash-lite-preview-09-2025", "model_name": "2.5 Flash Lite Preview 09 2025", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "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 }, "supports_image_size": false, "model_id": "2.5-flash-preview-09-2025", "model_name": "2.5 Flash Preview 09 2025", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 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": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 65536, "max_output_tokens": 32768, "input_cost_per_image": 0.0011, "input_cost_per_token_batches": 0.000001, "max_tokens": 32768, "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 0.000006, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_prompt_caching": true, "supports_system_messages": true, "supports_web_search": 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", "supports_service_tier": true, "model_id": "3-pro-image-preview", "model_name": "3 Pro Image Preview", "provider_id": "google", "provider_name": "Google", "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": "image", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65535, "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": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 65536, "max_output_tokens": 32768, "input_cost_per_token_batches": 1.25e-7, "max_tokens": 32768, "output_cost_per_image": 0.045, "output_cost_per_image_token": 0.00006, "output_cost_per_image_token_batches": 0.00003, "output_cost_per_token_batches": 7.5e-7, "rpm": 1000, "tpm": 4000000, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_prompt_caching": true, "supports_system_messages": true, "supports_web_search": 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-flash-image-preview", "model_name": "3.1 Flash Image Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "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_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_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, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_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", "model_name": "3.1 Flash Lite", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "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": 0.0000015, "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_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000009, "max_input_tokens": 1048576, "max_output_tokens": 65535, "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": 0.000009, "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_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-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": "3.5-flash", "model_name": "3.5 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 1.5, "output_cost_per_million": 9, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_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, "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, "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_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 7.5e-7, "max_input_tokens": 128000, "max_output_tokens": 50000, "max_tokens": 50000, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "inception/mercury-2", "model_name": "Mercury 2", "provider_id": "inception", "provider_name": "Inception", "input_cost_per_million": 0.25, "output_cost_per_million": 0.75, "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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/deepseek-llama3.3-70b", "model_name": "Deepseek Llama3.3 70B", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/deepseek-r1-0528", "model_name": "Deepseek R1 0528", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "lambda_ai/deepseek-r1-671b", "model_name": "Deepseek R1 671B", "provider_id": "lambda", "provider_name": "Lambda", "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 0.7999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 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, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 200000, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "model_id": "minimax/MiniMax-M2", "model_name": "MiniMax M2", "provider_id": "minimax", "provider_name": "MiniMax", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "model_id": "minimax/MiniMax-M2.1", "model_name": "MiniMax M2.1", "provider_id": "minimax", "provider_name": "MiniMax", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 1000000, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "model_id": "minimax/MiniMax-M2.1-lightning", "model_name": "MiniMax M2.1 Lightning", "provider_id": "minimax", "provider_name": "MiniMax", "input_cost_per_million": 0.3, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "model_id": "minimax/MiniMax-M2.5", "model_name": "MiniMax M2.5", "provider_id": "minimax", "provider_name": "MiniMax", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 1000000, "max_output_tokens": 8192, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "model_id": "minimax/MiniMax-M2.5-lightning", "model_name": "MiniMax M2.5 Lightning", "provider_id": "minimax", "provider_name": "MiniMax", "input_cost_per_million": 0.3, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 512000, "max_output_tokens": 128000, "supports_tool_choice": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "model_id": "minimax/MiniMax-M3", "model_name": "MiniMax M3", "provider_id": "minimax", "provider_name": "MiniMax", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 1.2e-7, "cache_read_cost_per_million": 0.12, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "input_cost_per_token": 8e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 16000, "max_output_tokens": 16000, "max_tokens": 16000, "supports_system_messages": true, "supports_tool_choice": false, "model_id": "morph/morph-v3-fast", "model_name": "Morph V3 Fast", "provider_id": "morph", "provider_name": "Morph", "input_cost_per_million": 0.7999999999999999, "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_parallel_functions": false, "supports_json_mode": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": false, "input_cost_per_token": 9e-7, "output_cost_per_token": 0.0000019, "max_input_tokens": 16000, "max_output_tokens": 16000, "max_tokens": 16000, "supports_system_messages": true, "supports_tool_choice": false, "model_id": "morph/morph-v3-large", "model_name": "Morph V3 Large", "provider_id": "morph", "provider_name": "Morph", "input_cost_per_million": 0.8999999999999999, "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_parallel_functions": false, "supports_json_mode": false }, { "input_cost_per_token": 7e-8, "output_cost_per_token": 7e-8, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "model_id": "novita/baichuan/baichuan-m2-32b", "model_name": "Baichuan M2 32B", "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_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": 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 }, { "input_cost_per_token": 7e-8, "output_cost_per_token": 2.8e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/baidu/ernie-4.5-21B-a3b-thinking", "model_name": "Ernie 4.5 21B A3B Thinking", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.07, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_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, "input_cost_per_token": 4.2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 123000, "max_output_tokens": 16000, "max_tokens": 16000, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/baidu/ernie-4.5-vl-424b-a47b", "model_name": "Ernie 4.5 Vl 424B A47B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.42, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_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 }, { "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 160000, "max_output_tokens": 160000, "max_tokens": 160000, "supports_system_messages": true, "model_id": "novita/deepseek/deepseek-prover-v2-671b", "model_name": "Deepseek Prover V2 671B", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 7e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "supports_tool_choice": true, "supports_system_messages": true, "input_cost_per_token_cache_hit": 3.5e-7, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-r1-0528", "model_name": "Deepseek R1 0528", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.7, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3.5e-7, "cache_read_cost_per_million": 0.35, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "input_cost_per_token": 6e-8, "output_cost_per_token": 9e-8, "max_input_tokens": 128000, "max_output_tokens": 32000, "max_tokens": 32000, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-r1-0528-qwen3-8b", "model_name": "Deepseek R1 0528 Qwen3 8B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.06, "output_cost_per_million": 0.09, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_response_schema": true, "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-r1-distill-llama-70b", "model_name": "Deepseek R1 Distill Llama 70B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 0.7999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_function_calling": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7, "max_input_tokens": 32768, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-r1-distill-qwen-14b", "model_name": "Deepseek R1 Distill Qwen 14B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.15, "output_cost_per_million": 0.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_function_calling": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 64000, "max_output_tokens": 32000, "max_tokens": 32000, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/deepseek/deepseek-r1-distill-qwen-32b", "model_name": "Deepseek R1 Distill Qwen 32B", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.3, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_function_calling": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "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_vision": true, "input_cost_per_token": 1.19e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 98304, "max_output_tokens": 16384, "max_tokens": 16384, "supports_system_messages": true, "model_id": "novita/google/gemma-3-27b-it", "model_name": "Gemma 3 27B It", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.119, "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_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 9e-8, "output_cost_per_token": 9e-8, "max_input_tokens": 4096, "max_output_tokens": 3200, "max_tokens": 3200, "supports_system_messages": true, "model_id": "novita/gryphe/mythomax-l2-13b", "model_name": "MythoMax-L2 (13B)", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.09, "output_cost_per_million": 0.09, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_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 }, { "input_cost_per_token": 4e-8, "output_cost_per_token": 4e-8, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "model_id": "novita/meta-llama/llama-3-8b-instruct", "model_name": "Llama 3 8B Instruct", "provider_id": "novita", "provider_name": "Novita", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-8, "output_cost_per_token": 5e-8, "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "supports_system_messages": true, "model_id": "novita/meta-llama/llama-3.1-8b-instruct", "model_name": "Llama 3.1 8B Instruct", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.02, "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_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": 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_vision": true, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 8.5e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "model_id": "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8", "model_name": "Llama 4 Maverick 17B 128e Instruct Fp8", "provider_id": "novita", "provider_name": "Novita", "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_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 1.8e-7, "output_cost_per_token": 5.9e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_system_messages": true, "model_id": "novita/meta-llama/llama-4-scout-17b-16e-instruct", "model_name": "Llama 4 Scout Instruct (17Bx16E)", "provider_id": "novita", "provider_name": "Novita", "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_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6.2e-7, "output_cost_per_token": 6.2e-7, "max_input_tokens": 65535, "max_output_tokens": 8000, "max_tokens": 8000, "supports_system_messages": true, "model_id": "novita/microsoft/wizardlm-2-8x22b", "model_name": "WizardLM-2 (8x22B)", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.62, "output_cost_per_million": 0.62, "cache_read_cost_per_token": 0, "cache_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": 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_vision": true, "input_cost_per_token": 2e-8, "output_cost_per_token": 2e-8, "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "supports_system_messages": true, "model_id": "novita/paddlepaddle/paddleocr-vl", "model_name": "Paddleocr Vl", "provider_id": "novita", "provider_name": "Novita", "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_function_calling": 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": 3.8e-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 }, { "input_cost_per_token": 2.5e-7, "output_cost_per_token": 7.5e-7, "max_input_tokens": 16384, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "model_id": "novita/qwen/qwen-mt-plus", "model_name": "Qwen Mt Plus", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.25, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 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_vision": true, "input_cost_per_token": 8e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 32768, "max_output_tokens": 32768, "max_tokens": 32768, "supports_system_messages": true, "model_id": "novita/qwen/qwen2.5-vl-72b-instruct", "model_name": "Qwen2.5 Vl 72B Instruct", "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_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 40960, "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/qwen/qwen3-235b-a22b-fp8", "model_name": "Qwen3 235B A22B Fp8", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.7999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 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 }, { "input_cost_per_token": 9e-8, "output_cost_per_token": 4.5e-7, "max_input_tokens": 40960, "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/qwen/qwen3-30b-a3b-fp8", "model_name": "Qwen3 30B A3B Fp8", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.09, "output_cost_per_million": 0.44999999999999996, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 4.5e-7, "max_input_tokens": 40960, "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/qwen/qwen3-32b-fp8", "model_name": "Qwen3 32B Fp8", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.44999999999999996, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-8, "output_cost_per_token": 3e-8, "max_input_tokens": 128000, "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/qwen/qwen3-4b-fp8", "model_name": "Qwen3 4B Fp8", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.03, "output_cost_per_million": 0.03, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3.5e-8, "output_cost_per_token": 1.38e-7, "max_input_tokens": 128000, "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/qwen/qwen3-8b-fp8", "model_name": "Qwen3 8B Fp8", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.035, "output_cost_per_million": 0.13799999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 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_vision": true, "input_cost_per_token": 9.8e-7, "output_cost_per_token": 0.00000395, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "supports_system_messages": true, "supports_reasoning": true, "model_id": "novita/qwen/qwen3-vl-235b-a22b-thinking", "model_name": "Qwen3 Vl 235B A22B Thinking", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.98, "output_cost_per_million": 3.95, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_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": 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_vision": true, "input_cost_per_token": 3.5e-8, "output_cost_per_token": 1.38e-7, "max_input_tokens": 65536, "max_output_tokens": 65536, "max_tokens": 65536, "supports_system_messages": true, "model_id": "novita/zai-org/autoglm-phone-9b-multilingual", "model_name": "Autoglm Phone 9B Multilingual", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.035, "output_cost_per_million": 0.13799999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "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, "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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_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": false, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-chat", "model_name": "GPT-5 Chat", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-chat-latest", "model_name": "GPT-5 Chat Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "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": 0.000002, "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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "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": false, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 16384, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.1-chat-latest", "model_name": "GPT-5.1 Chat Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "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": 0.00000175, "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": 0.000021, "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": 0.0000025, "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": 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": 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, "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, "supports_image_size": false, "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/gemini-api/docs/pricing#gemini-3.1-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_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", "model_name": "Gemini 3.1 Flash Lite", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": 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 }, { "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, "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": 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 }, { "input_cost_per_token": 0.00000375, "output_cost_per_token": 0.00001, "max_input_tokens": 65536, "max_output_tokens": 8192, "output_cost_per_reasoning_token": 0.00001, "max_tokens": 8192, "supports_reasoning": true, "supports_system_messages": true, "model_id": "deepseek-ai/deepseek-r1", "model_name": "DeepSeek R1", "provider_id": "replicate", "provider_name": "Replicate", "input_cost_per_million": 3.75, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000145, "output_cost_per_token": 0.00000145, "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "supports_system_messages": true, "model_id": "deepseek-ai/deepseek-v3", "model_name": "DeepSeek V3", "provider_id": "replicate", "provider_name": "Replicate", "input_cost_per_million": 1.4500000000000002, "output_cost_per_million": 1.4500000000000002, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6.72e-7, "output_cost_per_token": 0.000002016, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "supports_reasoning": true, "supports_system_messages": true, "model_id": "deepseek-ai/deepseek-v3.1", "model_name": "Deepseek V3.1", "provider_id": "replicate", "provider_name": "Replicate", "input_cost_per_million": 0.6719999999999999, "output_cost_per_million": 2.016, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "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, "supports_image_size": false, "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 }, { "supports_function_calling": true, "input_cost_per_token": 3e-8, "output_cost_per_token": 2.5e-7, "supports_system_messages": true, "model_id": "ibm-granite/granite-3.3-8b-instruct", "model_name": "Granite 3.3 8B Instruct", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.03, "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_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, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "supports_system_messages": true, "model_id": "openai/gpt-4.1-nano", "model_name": "GPT-4.1 nano", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "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, "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": 5e-8, "output_cost_per_token": 4e-7, "supports_system_messages": true, "model_id": "openai/gpt-5-nano", "model_name": "GPT-5 Nano", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "output_cost_per_reasoning_token": 0.00006, "supports_reasoning": true, "supports_system_messages": true, "model_id": "openai/o1", "model_name": "o1", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 15, "output_cost_per_million": 60, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "output_cost_per_reasoning_token": 0.0000044, "supports_reasoning": true, "supports_system_messages": true, "model_id": "openai/o1-mini", "model_name": "o1 mini", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000004, "output_cost_per_reasoning_token": 0.000004, "supports_reasoning": true, "supports_system_messages": true, "model_id": "openai/o4-mini", "model_name": "o4 mini", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.64e-7, "output_cost_per_token": 0.00000106, "supports_system_messages": true, "model_id": "qwen/qwen3-235b-a22b-instruct-2507", "model_name": "Qwen3 235B A22B Instruct (Jul 2025)", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.26399999999999996, "output_cost_per_million": 1.06, "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": 9e-8, "output_cost_per_token": 3.6e-7, "supports_system_messages": true, "model_id": "replicateopenai/gpt-oss-20b", "model_name": "GPT Oss 20B", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.09, "output_cost_per_million": 0.36, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000072, "output_cost_per_token": 0.000036, "supports_system_messages": true, "model_id": "xai/grok-4", "model_name": "Grok 4", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 7.199999999999999, "output_cost_per_million": 36, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_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": 16384, "max_tokens": 16384, "supports_computer_use": true, "supports_prompt_caching": true, "supports_system_messages": true, "model_id": "snowflake/claude-3-5-sonnet", "model_name": "Claude 3.5 Sonnet", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "snowflake/claude-3-7-sonnet", "model_name": "Claude 3 7 Sonnet", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "snowflake/claude-4-opus", "model_name": "Claude 4 Opus", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_system_messages": true, "model_id": "snowflake/claude-4-sonnet", "model_name": "Claude 4 Sonnet", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_system_messages": true, "model_id": "snowflake/claude-haiku-4-5", "model_name": "Claude Haiku 4 5", "provider_id": "snowflake", "provider_name": "Snowflake", "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, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_system_messages": true, "model_id": "snowflake/claude-sonnet-4-5", "model_name": "Claude Sonnet 4 5", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_system_messages": true, "model_id": "snowflake/claude-sonnet-4-6", "model_name": "Claude Sonnet 4 6", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_reasoning": true, "supports_system_messages": true, "model_id": "snowflake/deepseek-r1", "model_name": "DeepSeek R1", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 1.35, "output_cost_per_million": 5.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000012, "output_cost_per_token": 0.0000012, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_system_messages": true, "model_id": "snowflake/llama3.1-405b", "model_name": "Llama3.1 405B", "provider_id": "snowflake", "provider_name": "Snowflake", "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_vision": false, "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": 16384, "max_tokens": 16384, "supports_system_messages": true, "model_id": "snowflake/llama3.1-70b", "model_name": "Llama 3.1 70B", "provider_id": "snowflake", "provider_name": "Snowflake", "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": 2.4e-7, "output_cost_per_token": 2.4e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_system_messages": true, "model_id": "snowflake/llama3.1-8b", "model_name": "Llama 3.1 8B", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 0.24, "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_function_calling": false, "supports_vision": false, "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": 16384, "max_tokens": 16384, "supports_system_messages": true, "model_id": "snowflake/llama3.3-70b", "model_name": "Llama 3.3 70B", "provider_id": "snowflake", "provider_name": "Snowflake", "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 }, { "supports_function_calling": true, "input_cost_per_token": 2.4e-7, "output_cost_per_token": 9.7e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_system_messages": true, "model_id": "snowflake/llama4-maverick", "model_name": "Llama4 Maverick", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 0.24, "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_vision": false, "supports_json_mode": 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": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_system_messages": true, "model_id": "snowflake/mistral-large2", "model_name": "Mistral Large2", "provider_id": "snowflake", "provider_name": "Snowflake", "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 300000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_system_messages": true, "model_id": "snowflake/openai-gpt-4.1", "model_name": "Openai GPT-4.1", "provider_id": "snowflake", "provider_name": "Snowflake", "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": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 300000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_system_messages": true, "supports_reasoning": true, "model_id": "snowflake/openai-gpt-5", "model_name": "Openai GPT-5", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_system_messages": true, "model_id": "snowflake/openai-gpt-5-mini", "model_name": "Openai GPT-5 Mini", "provider_id": "snowflake", "provider_name": "Snowflake", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 5000000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_system_messages": true, "model_id": "snowflake/openai-gpt-5-nano", "model_name": "Openai GPT-5 Nano", "provider_id": "snowflake", "provider_name": "Snowflake", "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, "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_system_messages": true, "model_id": "snowflake/snowflake-llama-3.3-70b", "model_name": "Snowflake Llama 3.3 70B", "provider_id": "snowflake", "provider_name": "Snowflake", "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 }, { "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, "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, "supports_image_size": false, "model_id": "gemini-2.5-flash", "model_name": "Gemini 2.5 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "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, "supports_image_size": false, "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, "supports_image_size": false, "model_id": "gemini-2.5-flash-lite", "model_name": "Gemini 2.5 Flash Lite", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "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 }, "supports_image_size": false, "model_id": "gemini-2.5-flash-lite-preview-06-17", "model_name": "Gemini 2.5 Flash Lite Preview 06 17", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 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 }, "supports_image_size": false, "model_id": "gemini-2.5-flash-lite-preview-09-2025", "model_name": "Gemini 2.5 Flash Lite Preview 09 2025", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_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 }, "supports_image_size": false, "model_id": "gemini-2.5-flash-preview-09-2025", "model_name": "Gemini 2.5 Flash Preview 09 2025", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 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_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_per_audio_token": 5e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_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, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "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", "supports_service_tier": true, "model_id": "gemini-3.1-flash-lite", "model_name": "Gemini 3.1 Flash Lite", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "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": 0.0000015, "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": 0.0000015, "output_cost_per_token": 0.000009, "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": 0.000009, "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_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-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-3.5-flash", "model_name": "Gemini 3.5 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1.5, "output_cost_per_million": 9, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "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": 0.000002, "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 }, { "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, "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 } ]