[ { "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_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_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_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_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_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_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_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_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": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "source": "https://ai.azure.com/catalog/models/gpt-5.5", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure_ai/gpt-5.5", "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, "source": "https://ai.azure.com/catalog/models/gpt-5.5", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure_ai/gpt-5.5-2026-04-23", "model_name": "GPT-5.5 (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001375, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5-2025-08-07", "model_name": "GPT-5 (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.375, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.375e-7, "cache_read_cost_per_million": 0.1375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5-mini-2025-08-07", "model_name": "GPT-5 Mini (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.275, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 2.75e-8, "cache_read_cost_per_million": 0.0275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5.5e-8, "output_cost_per_token": 4.4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5-nano-2025-08-07", "model_name": "GPT-5 Nano (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.055, "output_cost_per_million": 0.44, "cache_read_cost_per_token": 5.5e-9, "cache_read_cost_per_million": 0.0055, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "model_id": "azure/eu/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "model_id": "azure/eu/gpt-5.1-chat", "model_name": "GPT-5.1 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.275, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.0000165, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 5.5e-7, "input_cost_per_token_priority": 0.0000055, "output_cost_per_token_priority": 0.000033, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.0000165, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 5.5e-7, "input_cost_per_token_priority": 0.0000055, "output_cost_per_token_priority": 0.000033, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5.4-2026-03-05", "model_name": "GPT-5.4 (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_priority": 0.00000138, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/eu/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_priority": 0.00000138, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/eu/gpt-5.5-2026-04-23", "model_name": "GPT-5.5 (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "model_id": "azure/global/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "model_id": "azure/global/gpt-5.1-chat", "model_name": "GPT-5.1 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/global/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/global/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "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": 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, "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": 0.00000125, "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_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": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-2025-11-13", "model_name": "GPT-5.1 Codex (Nov 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-max", "model_name": "GPT-5.1 Codex Max", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 128000, "output_cost_per_token_priority": 0.0000036, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-mini-2025-11-13", "model_name": "GPT-5.1 Codex Mini (Nov 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.2", "model_name": "GPT-5.2", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 128000, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "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, "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, "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, "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_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_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_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_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_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_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, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.0000088, "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 0.0000011, "max_tokens": 32768, "output_cost_per_token_batches": 0.0000044, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": false, "model_id": "azure/us/gpt-4.1-2025-04-14", "model_name": "GPT-4.1 (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.2, "output_cost_per_million": 8.8, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4.4e-7, "output_cost_per_token": 0.00000176, "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 2.2e-7, "max_tokens": 32768, "output_cost_per_token_batches": 8.8e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": false, "model_id": "azure/us/gpt-4.1-mini-2025-04-14", "model_name": "GPT-4.1 mini (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.44, "output_cost_per_million": 1.76, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.1e-7, "output_cost_per_token": 4.4e-7, "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 6e-8, "max_tokens": 32768, "output_cost_per_token_batches": 2.2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4.1-nano-2025-04-14", "model_name": "GPT-4.1 nano (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.11, "output_cost_per_million": 0.44, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001375, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-5-2025-08-07", "model_name": "GPT-5 (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.375, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.375e-7, "cache_read_cost_per_million": 0.1375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-5-mini-2025-08-07", "model_name": "GPT-5 Mini (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.275, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 2.75e-8, "cache_read_cost_per_million": 0.0275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5.5e-8, "output_cost_per_token": 4.4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-5-nano-2025-08-07", "model_name": "GPT-5 Nano (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.055, "output_cost_per_million": 0.44, "cache_read_cost_per_token": 5.5e-9, "cache_read_cost_per_million": 0.0055, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "model_id": "azure/us/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "model_id": "azure/us/gpt-5.1-chat", "model_name": "GPT-5.1 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/us/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/us/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.275, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.0000165, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 5.5e-7, "input_cost_per_token_priority": 0.0000055, "output_cost_per_token_priority": 0.000033, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.0000165, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 5.5e-7, "input_cost_per_token_priority": 0.0000055, "output_cost_per_token_priority": 0.000033, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-5.4-2026-03-05", "model_name": "GPT-5.4 (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_priority": 0.00000138, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/us/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_priority": 0.00000138, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/us/gpt-5.5-2026-04-23", "model_name": "GPT-5.5 (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "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": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000002, "max_tokens": 64000, "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_streaming": true, "supports_native_structured_output": true, "supports_parallel_tool_use_config": true, "model_id": "anthropic.claude-haiku-4-5@20251001", "model_name": "Claude Haiku 4 5@ (Oct 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-8, "output_cost_per_token": 1.65e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.darkbloom.dev/", "supported_endpoints": [ "/v1/chat/completions" ], "supports_native_streaming": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "darkbloom/gemma-4-26b", "model_name": "Gemma 4 26B", "provider_id": "darkbloom", "provider_name": "Darkbloom", "input_cost_per_million": 0.03, "output_cost_per_million": 0.165, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.45e-8, "output_cost_per_token": 7e-8, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://www.darkbloom.dev/", "supported_endpoints": [ "/v1/chat/completions" ], "supports_native_streaming": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "darkbloom/gpt-oss-20b", "model_name": "GPT Oss 20B", "provider_id": "darkbloom", "provider_name": "Darkbloom", "input_cost_per_million": 0.0145, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2.8e-7, "output_cost_per_token": 4.2e-7, "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "deepseek-chat", "model_name": "Deepseek Chat", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.28, "output_cost_per_million": 0.42, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_response_schema": true, "input_cost_per_token": 2.8e-7, "output_cost_per_token": 4.2e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "model_id": "deepseek-reasoner", "model_name": "Deepseek Reasoner", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.28, "output_cost_per_million": 0.42, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false, "supports_vision": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 1000000, "max_output_tokens": 8192, "input_cost_per_token_cache_hit": 2.8e-9, "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-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.14, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 2.8e-9, "cache_read_cost_per_million": 0.0028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 4.35e-7, "output_cost_per_token": 8.7e-7, "max_input_tokens": 1000000, "max_output_tokens": 8192, "input_cost_per_token_cache_hit": 3.625e-9, "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-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.435, "output_cost_per_million": 0.87, "cache_read_cost_per_token": 3.625e-9, "cache_read_cost_per_million": 0.003625, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_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_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 1000000, "max_output_tokens": 8192, "input_cost_per_token_cache_hit": 2.8e-9, "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-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.14, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 2.8e-9, "cache_read_cost_per_million": 0.0028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 4.35e-7, "output_cost_per_token": 8.7e-7, "max_input_tokens": 1000000, "max_output_tokens": 8192, "input_cost_per_token_cache_hit": 3.625e-9, "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-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "deepseek", "provider_name": "DeepSeek", "input_cost_per_million": 0.435, "output_cost_per_million": 0.87, "cache_read_cost_per_token": 3.625e-9, "cache_read_cost_per_million": 0.003625, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.000003, "rpm": 2000, "source": "https://ai.google.dev/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, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "model_id": "3-flash-preview", "model_name": "3 Flash Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_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_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "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, "input_cost_per_audio_token": 5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "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_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "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_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "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_tokens": 65535, "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, "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_response_schema": false, "input_cost_per_token": 0.00000156, "output_cost_per_token": 0.00000156, "max_input_tokens": 256000, "max_output_tokens": 4000, "max_tokens": 4000, "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", "supports_native_streaming": true, "model_id": "oci/cohere.command-a-03-2025", "model_name": "Cohere.command A 03 2025", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 1.56, "output_cost_per_million": 1.56, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_response_schema": false, "input_cost_per_token": 0.00000156, "output_cost_per_token": 0.00000156, "max_input_tokens": 256000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", "supports_native_streaming": true, "model_id": "oci/cohere.command-a-reasoning", "model_name": "Cohere.command A Reasoning", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 1.56, "output_cost_per_million": 1.56, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00000156, "output_cost_per_token": 0.00000156, "max_input_tokens": 256000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", "supports_native_streaming": true, "model_id": "oci/cohere.command-a-vision", "model_name": "Cohere.command A Vision", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 1.56, "output_cost_per_million": 1.56, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.00000156, "output_cost_per_token": 0.00000156, "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", "supports_native_streaming": true, "model_id": "oci/cohere.command-latest", "model_name": "Cohere.command Latest", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 1.56, "output_cost_per_million": 1.56, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.00000156, "output_cost_per_token": 0.00000156, "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", "supports_native_streaming": true, "model_id": "oci/cohere.command-plus-latest", "model_name": "Cohere.command Plus Latest", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 1.56, "output_cost_per_million": 1.56, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "supports_image_size": false, "model_id": "oci/google.gemini-2.5-flash", "model_name": "Google.gemini 2.5 Flash", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": 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": 65536, "max_tokens": 65536, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "supports_image_size": false, "model_id": "oci/google.gemini-2.5-flash-lite", "model_name": "Google.gemini 2.5 Flash Lite", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 0.075, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "model_id": "oci/google.gemini-2.5-pro", "model_name": "Google.gemini 2.5 Pro", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.00001068, "output_cost_per_token": 0.00001068, "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "model_id": "oci/meta.llama-3.1-405b-instruct", "model_name": "Meta.Llama 3.1 405B Instruct", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 10.68, "output_cost_per_million": 10.68, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7, "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "model_id": "oci/meta.llama-3.1-70b-instruct", "model_name": "Meta.Llama 3.1 70B Instruct", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 0.72, "output_cost_per_million": 0.72, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7, "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "model_id": "oci/meta.llama-3.1-8b-instruct", "model_name": "Meta.Llama 3.1 8B Instruct", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 0.72, "output_cost_per_million": 0.72, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000002, "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "model_id": "oci/meta.llama-3.2-90b-vision-instruct", "model_name": "Meta.Llama 3.2 90B Vision Instruct", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 2, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7, "max_input_tokens": 128000, "max_output_tokens": 4000, "max_tokens": 4000, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "model_id": "oci/meta.llama-3.3-70b-instruct", "model_name": "Meta.Llama 3.3 70B Instruct", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 0.72, "output_cost_per_million": 0.72, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "model_id": "oci/meta.llama-4-maverick-17b-128e-instruct-fp8", "model_name": "Meta.Llama 4 Maverick 17B 128e Instruct Fp8", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 0.72, "output_cost_per_million": 0.72, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 7.2e-7, "output_cost_per_token": 7.2e-7, "max_input_tokens": 10485760, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "model_id": "oci/meta.llama-4-scout-17b-16e-instruct", "model_name": "Meta.Llama 4 Scout 17B 16e Instruct", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 0.72, "output_cost_per_million": 0.72, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "supports_reasoning": true, "model_id": "oci/openai.gpt-5", "model_name": "Openai.GPT-5", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "supports_reasoning": true, "model_id": "oci/openai.gpt-5-mini", "model_name": "Openai.GPT-5 Mini", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "supports_reasoning": true, "model_id": "oci/openai.gpt-5-nano", "model_name": "Openai.GPT-5 Nano", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "model_id": "oci/xai.grok-3", "model_name": "Xai.grok 3", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "model_id": "oci/xai.grok-3-fast", "model_name": "Xai.grok 3 Fast", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 3e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "model_id": "oci/xai.grok-3-mini", "model_name": "Xai.grok 3 Mini", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 0.3, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "model_id": "oci/xai.grok-3-mini-fast", "model_name": "Xai.grok 3 Mini Fast", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 0.6, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_native_streaming": true, "model_id": "oci/xai.grok-4", "model_name": "Xai.grok 4", "provider_id": "oci", "provider_name": "Oci", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 1047576, "max_output_tokens": 32768, "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_priority": 0.0000035, "max_tokens": 32768, "output_cost_per_token_batches": 0.000004, "output_cost_per_token_priority": 0.000014, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_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_web_search": true, "model_id": "gpt-4.1-2025-04-14", "model_name": "GPT-4.1 (Apr 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "max_input_tokens": 1047576, "max_output_tokens": 32768, "cache_read_input_token_cost_priority": 1.75e-7, "input_cost_per_token_batches": 2e-7, "input_cost_per_token_priority": 7e-7, "max_tokens": 32768, "output_cost_per_token_batches": 8e-7, "output_cost_per_token_priority": 0.0000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_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_web_search": true, "model_id": "gpt-4.1-mini-2025-04-14", "model_name": "GPT-4.1 mini (Apr 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1047576, "max_output_tokens": 32768, "cache_read_input_token_cost_priority": 5e-8, "input_cost_per_token_batches": 5e-8, "input_cost_per_token_priority": 2e-7, "max_tokens": 32768, "output_cost_per_token_batches": 2e-7, "output_cost_per_token_priority": 8e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "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, "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": 0.00000125, "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_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_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": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-codex", "model_name": "GPT-5 Codex", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 128000, "output_cost_per_token_flex": 0.000001, "output_cost_per_token_priority": 0.0000036, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_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_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-mini-2025-08-07", "model_name": "GPT-5 Mini (Aug 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_flex": 2.5e-9, "input_cost_per_token_flex": 2.5e-8, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_flex": 2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-nano", "model_name": "GPT-5 Nano", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 5e-9, "cache_read_cost_per_million": 0.005, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_flex": 2.5e-9, "input_cost_per_token_flex": 2.5e-8, "max_tokens": 128000, "output_cost_per_token_flex": 2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-nano-2025-08-07", "model_name": "GPT-5 Nano (Aug 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 5e-9, "cache_read_cost_per_million": 0.005, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "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_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_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": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.1-codex-max", "model_name": "GPT-5.1 Codex Max", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 128000, "output_cost_per_token_priority": 0.0000036, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 128000, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_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_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.2-2025-12-11", "model_name": "GPT-5.2 (Dec 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 128000, "max_output_tokens": 16384, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 16384, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.2-chat-latest", "model_name": "GPT-5.2 Chat Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 128000, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.2-codex", "model_name": "GPT-5.2 Codex", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.2-pro", "model_name": "GPT-5.2 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 21, "output_cost_per_million": 168, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.2-pro-2025-12-11", "model_name": "GPT-5.2 Pro (Dec 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 21, "output_cost_per_million": 168, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 128000, "max_output_tokens": 16384, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 16384, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.3-chat-latest", "model_name": "GPT-5.3 Chat Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 128000, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.3-codex", "model_name": "GPT-5.3 Codex", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_flex": 1.3e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_flex": 0.00000125, "input_cost_per_token_batches": 0.00000125, "input_cost_per_token_priority": 0.000005, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_flex": 0.0000075, "output_cost_per_token_batches": 0.0000075, "output_cost_per_token_priority": 0.00003, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "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, "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, "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": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_priority": 0.0000015, "max_tokens": 128000, "output_cost_per_token_flex": 0.00000225, "output_cost_per_token_batches": 0.00000225, "output_cost_per_token_priority": 0.000009, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "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": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_priority": 0.0000015, "max_tokens": 128000, "output_cost_per_token_flex": 0.00000225, "output_cost_per_token_batches": 0.00000225, "output_cost_per_token_priority": 0.000009, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "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": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_flex": 1e-8, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_batches": 1e-7, "max_tokens": 128000, "output_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 6.25e-7, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "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": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_flex": 1e-8, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_batches": 1e-7, "max_tokens": 128000, "output_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 6.25e-7, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": 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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": 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, "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_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, "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_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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false, "model_id": "gpt-5.5-pro", "model_name": "GPT-5.5 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "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, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false, "model_id": "gpt-5.5-pro-2026-04-23", "model_name": "GPT-5.5 Pro (Apr 2026)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "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_creation_input_token_cost_above_272k_tokens": 0.0000125, "cache_creation_input_token_cost_flex": 0.000003125, "cache_creation_input_token_cost_priority": 0.0000125, "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_batches": 0.0000025, "input_cost_per_token_flex": 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_batches": 0.000015, "output_cost_per_token_flex": 0.000015, "output_cost_per_token_priority": 0.00006, "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_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-5.6", "model_name": "GPT-5.6", "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": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000006, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.0000025, "cache_creation_input_token_cost_flex": 6.25e-7, "cache_creation_input_token_cost_priority": 0.0000025, "cache_read_input_token_cost_above_272k_tokens": 2e-7, "cache_read_input_token_cost_flex": 5e-8, "cache_read_input_token_cost_priority": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000002, "input_cost_per_token_batches": 5e-7, "input_cost_per_token_flex": 5e-7, "input_cost_per_token_priority": 0.000002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000009, "output_cost_per_token_batches": 0.000003, "output_cost_per_token_flex": 0.000003, "output_cost_per_token_priority": 0.000012, "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_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1, "output_cost_per_million": 6, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": 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_creation_input_token_cost_above_272k_tokens": 0.0000125, "cache_creation_input_token_cost_flex": 0.000003125, "cache_creation_input_token_cost_priority": 0.0000125, "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_batches": 0.0000025, "input_cost_per_token_flex": 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_batches": 0.000015, "output_cost_per_token_flex": 0.000015, "output_cost_per_token_priority": 0.00006, "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_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-5.6-sol", "model_name": "GPT-5.6 Sol", "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": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00000625, "cache_creation_input_token_cost_flex": 0.0000015625, "cache_creation_input_token_cost_priority": 0.00000625, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_flex": 1.25e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_batches": 0.00000125, "input_cost_per_token_flex": 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_batches": 0.0000075, "output_cost_per_token_flex": 0.0000075, "output_cost_per_token_priority": 0.00003, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-5.6-terra", "model_name": "GPT-5.6 Terra", "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": 0.000003125, "cache_write_cost_per_million": 3.125, "model_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": 0.000032, "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, "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_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 1.4e-7, "output_cost_per_token": 2.8e-7, "max_input_tokens": 1000000, "max_output_tokens": 384000, "input_cost_per_token_cache_hit": 2.8e-9, "max_tokens": 384000, "source": "https://www.tencentcloud.com/products/tokenhub", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_reasoning": true, "model_id": "tencent/deepseek-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "tencent", "provider_name": "Tencent", "input_cost_per_million": 0.14, "output_cost_per_million": 0.28, "cache_read_cost_per_token": 2.8e-9, "cache_read_cost_per_million": 0.0028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 4.35e-7, "output_cost_per_token": 8.7e-7, "max_input_tokens": 1000000, "max_output_tokens": 384000, "input_cost_per_token_cache_hit": 3.625e-9, "max_tokens": 384000, "source": "https://www.tencentcloud.com/products/tokenhub", "supported_endpoints": [ "/v1/chat/completions" ], "supports_assistant_prefill": true, "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_reasoning": true, "model_id": "tencent/deepseek-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "tencent", "provider_name": "Tencent", "input_cost_per_million": 0.435, "output_cost_per_million": 0.87, "cache_read_cost_per_token": 3.625e-9, "cache_read_cost_per_million": 0.003625, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 8192, "cache_creation_input_token_cost_above_1hr": 0.000002, "max_tokens": 8192, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", "supports_assistant_prefill": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_streaming": true, "model_id": "claude-haiku-4-5", "model_name": "Claude Haiku 4 5", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 8192, "cache_creation_input_token_cost_above_1hr": 0.000002, "max_tokens": 8192, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", "supports_assistant_prefill": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_streaming": true, "model_id": "claude-haiku-4-5@20251001", "model_name": "Claude Haiku 4 5@ (Oct 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_streaming": true, "supports_output_config": true, "model_id": "claude-opus-4-5@20251101", "model_name": "Claude Opus 4 5@ (Nov 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_batches": 0.0000015, "max_tokens": 64000, "output_cost_per_token_batches": 0.0000075, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_streaming": true, "model_id": "claude-sonnet-4-5@20250929", "model_name": "Claude Sonnet 4 5@ (Sep 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.000003, "source": "https://ai.google.dev/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, "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_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "model_id": "gemini-3-pro-preview", "model_name": "Gemini 3 Pro Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "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, "input_cost_per_audio_token": 5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "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_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "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_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "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_tokens": 65535, "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, "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 } ]