[ { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000006, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-15", "max_tokens": 100000, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure_ai/codex-mini", "model_name": "Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.5, "output_cost_per_million": 6, "cache_read_cost_per_token": 3.75e-7, "cache_read_cost_per_million": 0.375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-09-07", "cache_read_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_priority": 0.000006, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000012, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_priority": 0.00006, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_priority": 0.00036, "output_cost_per_token_above_272k_tokens_priority": 0.00054, "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure_ai/gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-09-07", "cache_read_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_priority": 0.000006, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000012, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_priority": 0.00006, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_priority": 0.00036, "output_cost_per_token_above_272k_tokens_priority": 0.00054, "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure_ai/gpt-5.4-pro-2026-03-05", "model_name": "GPT-5.4 Pro (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000006, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-15", "max_tokens": 100000, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/codex-mini", "model_name": "Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.5, "output_cost_per_million": 6, "cache_read_cost_per_token": 3.75e-7, "cache_read_cost_per_million": 0.375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "input_cost_per_token": 0.00000165, "output_cost_per_token": 0.0000066, "deprecation_date": "2026-11-15", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/eu/codex-mini", "model_name": "Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.6500000000000001, "output_cost_per_million": 6.6000000000000005, "cache_read_cost_per_token": 4.13e-7, "cache_read_cost_per_million": 0.413, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000001375, "output_cost_per_token": 0.000011, "deprecation_date": "2027-03-17", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/eu/gpt-5-codex", "model_name": "GPT-5 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.375, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.38e-7, "cache_read_cost_per_million": 0.13799999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000165, "output_cost_per_token": 0.000132, "deprecation_date": "2027-04-07", "input_cost_per_token_batches": 0.00000825, "output_cost_per_token_batches": 0.000066, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/eu/gpt-5-pro", "model_name": "GPT-5 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 16.5, "output_cost_per_million": 132, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001375, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.375, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.375e-7, "cache_read_cost_per_million": 0.1375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "input_cost_per_token": 0.000001375, "output_cost_per_token": 0.000011, "deprecation_date": "2027-05-18", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/eu/gpt-5.1-codex-max", "model_name": "GPT-5.1 Codex Max", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "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": "responses", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.275, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 2.75e-8, "cache_read_cost_per_million": 0.0275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "input_cost_per_token": 0.000001925, "output_cost_per_token": 0.0000154, "deprecation_date": "2027-07-13", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/eu/gpt-5.2-codex", "model_name": "GPT-5.2 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.9250000000000003, "output_cost_per_million": 15.400000000000002, "cache_read_cost_per_token": 1.925e-7, "cache_read_cost_per_million": 0.1925, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000231, "output_cost_per_token": 0.0001848, "input_cost_per_token_batches": 0.00001155, "output_cost_per_token_batches": 0.0000924, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/eu/gpt-5.2-pro", "model_name": "GPT-5.2 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 23.099999999999998, "output_cost_per_million": 184.79999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000001925, "output_cost_per_token": 0.0000154, "deprecation_date": "2027-08-24", "cache_read_input_token_cost_priority": 3.85e-7, "input_cost_per_token_priority": 0.00000385, "output_cost_per_token_priority": 0.0000308, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/eu/gpt-5.3-codex", "model_name": "GPT-5.3 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.9250000000000003, "output_cost_per_million": 15.400000000000002, "cache_read_cost_per_token": 1.925e-7, "cache_read_cost_per_million": 0.1925, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000033, "output_cost_per_token": 0.000198, "deprecation_date": "2027-09-07", "input_cost_per_token_above_272k_tokens": 0.000066, "input_cost_per_token_above_272k_tokens_batches": 0.000033, "input_cost_per_token_batches": 0.0000165, "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_above_272k_tokens_batches": 0.0001485, "output_cost_per_token_batches": 0.000099, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/eu/gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 33, "output_cost_per_million": 198, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/global/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/global/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-03-17", "max_tokens": 128000, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-codex", "model_name": "GPT-5 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00012, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-04-07", "input_cost_per_token_batches": 0.0000075, "max_tokens": 128000, "output_cost_per_token_batches": 0.00006, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-pro", "model_name": "GPT-5 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 15, "output_cost_per_million": 120, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_priority": 0.00002, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-2025-11-13", "model_name": "GPT-5.1 Codex (Nov 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-18", "max_tokens": 128000, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-max", "model_name": "GPT-5.1 Codex Max", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 128000, "output_cost_per_token_priority": 0.0000036, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-mini-2025-11-13", "model_name": "GPT-5.1 Codex Mini (Nov 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-07-13", "max_tokens": 128000, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.2-codex", "model_name": "GPT-5.2 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168, "max_input_tokens": 272000, "max_output_tokens": 128000, "input_cost_per_token_batches": 0.0000105, "max_tokens": 128000, "output_cost_per_token_batches": 0.000084, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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, "input_cost_per_token_batches": 0.0000105, "max_tokens": 128000, "output_cost_per_token_batches": 0.000084, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.2-pro-2025-12-11", "model_name": "GPT-5.2 Pro (Dec 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 21, "output_cost_per_million": 168, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-08-24", "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 128000, "output_cost_per_token_priority": 0.000028, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.3-codex", "model_name": "GPT-5.3 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-09-07", "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_above_272k_tokens_batches": 0.00003, "input_cost_per_token_above_272k_tokens_flex": 0.00003, "input_cost_per_token_batches": 0.000015, "input_cost_per_token_flex": 0.000015, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "output_cost_per_token_above_272k_tokens_flex": 0.000135, "output_cost_per_token_batches": 0.00009, "output_cost_per_token_flex": 0.00009, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-09-07", "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_above_272k_tokens_flex": 0.00003, "input_cost_per_token_batches": 0.000015, "input_cost_per_token_flex": 0.000015, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_above_272k_tokens_flex": 0.000135, "output_cost_per_token_batches": 0.00009, "output_cost_per_token_flex": 0.00009, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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, "input_cost_per_token_above_272k_tokens_batches": 0.00003, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "model_id": "azure/gpt-5.4-pro-2026-03-05", "model_name": "GPT-5.4 Pro (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false, "model_id": "azure/gpt-5.5-pro", "model_name": "GPT-5.5 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.5-pro-2026-04-23", "model_name": "GPT-5.5 Pro (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00004, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "max_tokens": 100000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/o3-deep-research", "model_name": "O3 Deep Research", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 40, "cache_read_cost_per_token": 0.0000025, "cache_read_cost_per_million": 2.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00002, "output_cost_per_token": 0.00008, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "input_cost_per_token_batches": 0.00001, "max_tokens": 100000, "output_cost_per_token_batches": 0.00004, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o3-pro", "model_name": "o3 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 20, "output_cost_per_million": 80, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00002, "output_cost_per_token": 0.00008, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "input_cost_per_token_batches": 0.00001, "max_tokens": 100000, "output_cost_per_token_batches": 0.00004, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o3-pro-2025-06-10", "model_name": "o3 Pro (Jun 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 20, "output_cost_per_million": 80, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000165, "output_cost_per_token": 0.0000066, "deprecation_date": "2026-11-15", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/us/codex-mini", "model_name": "Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.6500000000000001, "output_cost_per_million": 6.6000000000000005, "cache_read_cost_per_token": 4.13e-7, "cache_read_cost_per_million": 0.413, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000001375, "output_cost_per_token": 0.000011, "deprecation_date": "2027-03-17", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/us/gpt-5-codex", "model_name": "GPT-5 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.375, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.38e-7, "cache_read_cost_per_million": 0.13799999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000165, "output_cost_per_token": 0.000132, "deprecation_date": "2027-04-07", "input_cost_per_token_batches": 0.00000825, "output_cost_per_token_batches": 0.000066, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/us/gpt-5-pro", "model_name": "GPT-5 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 16.5, "output_cost_per_million": 132, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001375, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/us/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.375, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.375e-7, "cache_read_cost_per_million": 0.1375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "input_cost_per_token": 0.000001375, "output_cost_per_token": 0.000011, "deprecation_date": "2027-05-18", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/us/gpt-5.1-codex-max", "model_name": "GPT-5.1 Codex Max", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "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": "responses", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-05-15", "max_tokens": 128000, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/us/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.275, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 2.75e-8, "cache_read_cost_per_million": 0.0275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "input_cost_per_token": 0.000001925, "output_cost_per_token": 0.0000154, "deprecation_date": "2027-07-13", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/us/gpt-5.2-codex", "model_name": "GPT-5.2 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.9250000000000003, "output_cost_per_million": 15.400000000000002, "cache_read_cost_per_token": 1.925e-7, "cache_read_cost_per_million": 0.1925, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000231, "output_cost_per_token": 0.0001848, "input_cost_per_token_batches": 0.00001155, "output_cost_per_token_batches": 0.0000924, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/us/gpt-5.2-pro", "model_name": "GPT-5.2 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 23.099999999999998, "output_cost_per_million": 184.79999999999998, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000001925, "output_cost_per_token": 0.0000154, "deprecation_date": "2027-08-24", "cache_read_input_token_cost_priority": 3.85e-7, "input_cost_per_token_priority": 0.00000385, "output_cost_per_token_priority": 0.0000308, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/us/gpt-5.3-codex", "model_name": "GPT-5.3 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.9250000000000003, "output_cost_per_million": 15.400000000000002, "cache_read_cost_per_token": 1.925e-7, "cache_read_cost_per_million": 0.1925, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000033, "output_cost_per_token": 0.000198, "deprecation_date": "2027-09-07", "input_cost_per_token_above_272k_tokens": 0.000066, "input_cost_per_token_above_272k_tokens_batches": 0.000033, "input_cost_per_token_batches": 0.0000165, "output_cost_per_token_above_272k_tokens": 0.000297, "output_cost_per_token_above_272k_tokens_batches": 0.0001485, "output_cost_per_token_batches": 0.000099, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/us/gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 33, "output_cost_per_million": 198, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.0000165, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 5.5e-7, "output_cost_per_token_above_272k_tokens": 0.00002475, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "model_id": "bedrock_mantle/openai.gpt-5.4", "model_name": "Openai.GPT-5.4", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 2.75e-7, "cache_read_cost_per_million": 0.275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.000011, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "output_cost_per_token_above_272k_tokens": 0.0000495, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html", "model_id": "bedrock_mantle/openai.gpt-5.5", "model_name": "Openai.GPT-5.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001375, "output_cost_per_token": 0.0000825, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "bedrock_mantle/openai.gpt-5.6-cyber", "model_name": "Openai.GPT-5.6 Cyber", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 13.75, "output_cost_per_million": 82.5, "cache_read_cost_per_token": 0.000001375, "cache_read_cost_per_million": 1.375, "cache_write_cost_per_token": 0.0000171875, "cache_write_cost_per_million": 17.1875, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.2e-7, "output_cost_per_token": 0.00000132, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 4.4e-7, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-7, "cache_read_input_token_cost_above_272k_tokens": 4.4e-8, "output_cost_per_token_above_272k_tokens": 0.00000198, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "model_id": "bedrock_mantle/openai.gpt-5.6-luna", "model_name": "Openai.GPT-5.6 Luna", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.22, "output_cost_per_million": 1.32, "cache_read_cost_per_token": 2.2e-8, "cache_read_cost_per_million": 0.022, "cache_write_cost_per_token": 2.75e-7, "cache_write_cost_per_million": 0.275, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000044, "output_cost_per_token": 0.000022, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.0000088, "cache_creation_input_token_cost_above_272k_tokens": 0.000011, "cache_read_input_token_cost_above_272k_tokens": 8.8e-7, "output_cost_per_token_above_272k_tokens": 0.000033, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "model_id": "bedrock_mantle/openai.gpt-5.6-sol", "model_name": "Openai.GPT-5.6 Sol", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 4.4, "output_cost_per_million": 22, "cache_read_cost_per_token": 4.4e-7, "cache_read_cost_per_million": 0.44, "cache_write_cost_per_token": 0.0000055, "cache_write_cost_per_million": 5.5, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.0000132, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.0000044, "cache_creation_input_token_cost_above_272k_tokens": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 4.4e-7, "output_cost_per_token_above_272k_tokens": 0.0000198, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "model_id": "bedrock_mantle/openai.gpt-5.6-terra", "model_name": "Openai.GPT-5.6 Terra", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.2, "output_cost_per_million": 13.200000000000001, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000011, "output_cost_per_token": 0.000055, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.000022, "cache_creation_input_token_cost_above_272k_tokens": 0.0000275, "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.000165, "cache_creation_input_token_cost_ultrafast": 0.0000825, "cache_read_input_token_cost_above_272k_tokens": 0.0000022, "cache_read_input_token_cost_above_272k_tokens_ultrafast": 0.0000132, "cache_read_input_token_cost_ultrafast": 0.0000066, "input_cost_per_token_above_272k_tokens_ultrafast": 0.000132, "input_cost_per_token_ultrafast": 0.000066, "output_cost_per_token_above_272k_tokens": 0.0000825, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens_ultrafast": 0.000495, "output_cost_per_token_ultrafast": 0.00033, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html", "model_id": "bedrock_mantle/openai.gpt-6-astra", "model_name": "Openai.GPT-6 Astra", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 11, "output_cost_per_million": 55, "cache_read_cost_per_token": 0.0000011, "cache_read_cost_per_million": 1.1, "cache_write_cost_per_token": 0.00001375, "cache_write_cost_per_million": 13.75, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.1e-7, "output_cost_per_token": 5.5e-7, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 2.2e-7, "cache_creation_input_token_cost_above_272k_tokens": 2.75e-7, "cache_read_input_token_cost_above_272k_tokens": 2.2e-8, "output_cost_per_token_above_272k_tokens": 8.25e-7, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html", "model_id": "bedrock_mantle/openai.gpt-6-luna", "model_name": "Openai.GPT-6 Luna", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.11, "output_cost_per_million": 0.55, "cache_read_cost_per_token": 1.1e-8, "cache_read_cost_per_million": 0.011, "cache_write_cost_per_token": 1.375e-7, "cache_write_cost_per_million": 0.1375, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.000011, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.0000044, "cache_creation_input_token_cost_above_272k_tokens": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 4.4e-7, "output_cost_per_token_above_272k_tokens": 0.0000165, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html", "model_id": "bedrock_mantle/openai.gpt-6-sol", "model_name": "Openai.GPT-6 Sol", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.2, "output_cost_per_million": 11, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.000011, "max_input_tokens": 1050000, "max_output_tokens": 131072, "cache_creation_input_token_cost_above_272k_tokens": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 2.2e-7, "input_cost_per_token_above_272k_tokens": 0.0000044, "max_tokens": 131072, "output_cost_per_token_above_272k_tokens": 0.0000165, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "use_openai_responses_path": true, "model_id": "bedrock_mantle/openai.gpt-6.1-sol", "model_name": "Openai.GPT-6.1 Sol", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.2, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000044, "output_cost_per_token": 0.000022, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.0000088, "cache_creation_input_token_cost_above_272k_tokens": 0.000011, "cache_read_input_token_cost_above_272k_tokens": 8.8e-7, "output_cost_per_token_above_272k_tokens": 0.000033, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-daybreak-blue-56-sol.html", "model_id": "bedrock_mantle/openai.gpt-daybreak-blue-5.6-sol", "model_name": "Openai.GPT Daybreak Blue 5.6 Sol", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 4.4, "output_cost_per_million": 22, "cache_read_cost_per_token": 4.4e-7, "cache_read_cost_per_million": 0.44, "cache_write_cost_per_token": 0.0000055, "cache_write_cost_per_million": 5.5, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000033, "output_cost_per_token": 0.0000198, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "model_id": "bedrock_mantle/us-gov-east-1/openai.gpt-5.4", "model_name": "Openai.GPT-5.4", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.3000000000000003, "output_cost_per_million": 19.8, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003375, "output_cost_per_token": 0.00002025, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "model_id": "bedrock_mantle/us-gov-west-1/openai.gpt-5.4", "model_name": "Openai.GPT-5.4", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 3.375, "output_cost_per_million": 20.25, "cache_read_cost_per_token": 3.375e-7, "cache_read_cost_per_million": 0.3375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.7e-7, "output_cost_per_token": 0.00000162, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "input_cost_per_token_above_272k_tokens": 5.4e-7, "cache_creation_input_token_cost_above_272k_tokens": 6.75e-7, "cache_read_input_token_cost_above_272k_tokens": 5.4e-8, "output_cost_per_token_above_272k_tokens": 0.00000243, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "model_id": "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna", "model_name": "Openai.GPT-5.6 Luna", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.27, "output_cost_per_million": 1.6199999999999999, "cache_read_cost_per_token": 2.7e-8, "cache_read_cost_per_million": 0.027, "cache_write_cost_per_token": 3.375e-7, "cache_write_cost_per_million": 0.3375, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000027, "output_cost_per_token": 0.0000162, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "input_cost_per_token_above_272k_tokens": 0.0000054, "cache_creation_input_token_cost_above_272k_tokens": 0.00000675, "cache_read_input_token_cost_above_272k_tokens": 5.4e-7, "output_cost_per_token_above_272k_tokens": 0.0000243, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "model_id": "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra", "model_name": "Openai.GPT-5.6 Terra", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.7, "output_cost_per_million": 16.2, "cache_read_cost_per_token": 2.7e-7, "cache_read_cost_per_million": 0.27, "cache_write_cost_per_token": 0.000003375, "cache_write_cost_per_million": 3.375, "model_type": "responses", "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, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supports_reasoning": true, "model_id": "chatgpt/gpt-5.1-codex-max", "model_name": "GPT-5.1 Codex Max", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "supported_endpoints": [ "/v1/responses" ], "supports_reasoning": true, "model_id": "chatgpt/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "chatgpt/gpt-5.2", "model_name": "GPT-5.2", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supports_reasoning": true, "model_id": "chatgpt/gpt-5.2-codex", "model_name": "GPT-5.2 Codex", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "model_id": "chatgpt/gpt-5.3-chat-latest", "model_name": "GPT-5.3 Chat Latest", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supports_reasoning": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "chatgpt/gpt-5.3-codex", "model_name": "GPT-5.3 Codex", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "model_id": "chatgpt/gpt-5.3-codex-spark", "model_name": "GPT-5.3 Codex Spark", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "model_id": "chatgpt/gpt-5.3-instant", "model_name": "GPT-5.3 Instant", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "chatgpt/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supports_reasoning": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "chatgpt/gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 1050000, "max_output_tokens": 128000, "source": "https://platform.openai.com/docs/models/gpt-5.5", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_reasoning": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "chatgpt/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 1050000, "max_output_tokens": 128000, "source": "https://platform.openai.com/docs/models/gpt-5.6-luna", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "model_id": "chatgpt/gpt-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 1050000, "max_output_tokens": 128000, "source": "https://platform.openai.com/docs/models/gpt-5.6-sol", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "model_id": "chatgpt/gpt-5.6-sol", "model_name": "GPT-5.6 Sol", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 1050000, "max_output_tokens": 128000, "source": "https://platform.openai.com/docs/models/gpt-5.6-terra", "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "model_id": "chatgpt/gpt-5.6-terra", "model_name": "GPT-5.6 Terra", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 922000, "max_output_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/pricing", "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "model_id": "chatgpt/gpt-6-astra", "model_name": "GPT-6 Astra", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 922000, "max_output_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/pricing", "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "model_id": "chatgpt/gpt-6-luna", "model_name": "GPT-6 Luna", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 922000, "max_output_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/pricing", "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": true, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "model_id": "chatgpt/gpt-6-sol", "model_name": "GPT-6 Sol", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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, "max_input_tokens": 922000, "max_output_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/pricing", "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_none_reasoning_effort": false, "supports_reasoning": true, "supports_xhigh_reasoning_effort": true, "model_id": "chatgpt/gpt-6.1-sol", "model_name": "GPT-6.1 Sol", "provider_id": "chatgpt", "provider_name": "Chatgpt", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000025, "max_tokens": 128000, "metadata": { "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." }, "output_dbu_cost_per_token": 0.0002, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "databricks-gpt-5-3-codex", "model_name": "Databricks GPT-5 3 Codex", "provider_id": "databricks", "provider_name": "Databricks", "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": 0.00000175, "cache_write_cost_per_million": 1.75, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000500003, "output_cost_per_token": 0.00002999997, "max_input_tokens": 922000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000071429, "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.000428571, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gpt-5-5", "model_name": "Databricks GPT-5 5", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 5.00003, "output_cost_per_million": 29.999969999999998, "cache_read_cost_per_token": 5.0001e-7, "cache_read_cost_per_million": 0.5000100000000001, "cache_write_cost_per_token": 0.00000500003, "cache_write_cost_per_million": 5.00003, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00002999997, "output_cost_per_token": 0.00018000003, "max_input_tokens": 922000, "max_output_tokens": 128000, "input_dbu_cost_per_token": 0.000428571, "max_tokens": 128000, "metadata": { "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "output_dbu_cost_per_token": 0.002571429, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "databricks-gpt-5-5-pro", "model_name": "Databricks GPT-5 5 Pro", "provider_id": "databricks", "provider_name": "Databricks", "input_cost_per_million": 29.999969999999998, "output_cost_per_million": 180.00003, "cache_read_cost_per_token": 0.00002999997, "cache_read_cost_per_million": 29.999969999999998, "cache_write_cost_per_token": 0.00002999997, "cache_write_cost_per_million": 29.999969999999998, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "model_id": "github_copilot/gpt-5.1-codex-max", "model_name": "GPT-5.1 Codex Max", "provider_id": "github", "provider_name": "Github", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "model_id": "github_copilot/gpt-5.3-codex", "model_name": "GPT-5.3 Codex", "provider_id": "github", "provider_name": "Github", "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": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-07-23", "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/models/gpt-5-codex", "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_tool_choice": true, "supports_web_search": true, "model_id": "gpt-5-codex", "model_name": "GPT-5 Codex", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00012, "max_input_tokens": 400000, "max_output_tokens": 272000, "input_cost_per_token_batches": 0.0000075, "max_tokens": 272000, "output_cost_per_token_batches": 0.00006, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-pro", "model_name": "GPT-5 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 15, "output_cost_per_million": 120, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00012, "max_input_tokens": 400000, "max_output_tokens": 272000, "deprecation_date": "2026-12-11", "input_cost_per_token_batches": 0.0000075, "max_tokens": 272000, "output_cost_per_token_batches": 0.00006, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-pro-2025-10-06", "model_name": "GPT-5 Pro (Oct 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 15, "output_cost_per_million": 120, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 400000, "max_output_tokens": 128000, "deprecation_date": "2026-07-23", "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex", "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_tool_choice": true, "supports_web_search": true, "model_id": "gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 400000, "max_output_tokens": 128000, "deprecation_date": "2026-07-23", "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-max", "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_tool_choice": true, "supports_web_search": true, "model_id": "gpt-5.1-codex-max", "model_name": "GPT-5.1 Codex Max", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 400000, "max_output_tokens": 128000, "deprecation_date": "2026-07-23", "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-mini", "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_tool_choice": true, "model_id": "gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-07-23", "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-codex", "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_tool_choice": true, "supports_web_search": true, "model_id": "gpt-5.2-codex", "model_name": "GPT-5.2 Codex", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168, "max_input_tokens": 272000, "max_output_tokens": 128000, "input_cost_per_token_batches": 0.0000105, "max_tokens": 128000, "output_cost_per_token_batches": 0.000084, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "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, "input_cost_per_token_batches": 0.0000105, "max_tokens": 128000, "output_cost_per_token_batches": 0.000084, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "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": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-04-01", "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 128000, "output_cost_per_token_priority": 0.000028, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "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", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "input_cost_per_token_above_272k_tokens_batches": 0.00003, "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, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 0.00003, "output_cost_per_token_above_272k_tokens_flex": 0.000135, "source": "https://developers.openai.com/api/docs/pricing", "model_id": "gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "input_cost_per_token_above_272k_tokens_batches": 0.00003, "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, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "input_cost_per_token_above_272k_tokens_flex": 0.00003, "output_cost_per_token_above_272k_tokens_flex": 0.000135, "source": "https://developers.openai.com/api/docs/pricing", "model_id": "gpt-5.4-pro-2026-03-05", "model_name": "GPT-5.4 Pro (Mar 2026)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "input_cost_per_token_above_272k_tokens_batches": 0.00003, "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, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false, "model_id": "gpt-5.5-pro", "model_name": "GPT-5.5 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "input_cost_per_token_above_272k_tokens_batches": 0.00003, "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, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false, "model_id": "gpt-5.5-pro-2026-04-23", "model_name": "GPT-5.5 Pro (Apr 2026)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00001, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "input_cost_per_token_above_272k_tokens": 0.000008, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00003, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", "model_id": "gpt-daybreak-blue-latest", "model_name": "GPT Daybreak Blue Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 5, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000125, "output_cost_per_token": 0.000075, "max_input_tokens": 400000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00003125, "cache_read_input_token_cost_above_272k_tokens": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000025, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0001125, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", "supports_computer_use": true, "model_id": "gpt-daybreak-red-latest", "model_name": "GPT Daybreak Red Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 12.5, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0.000015625, "cache_write_cost_per_million": 15.625, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00015, "output_cost_per_token": 0.0006, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-10-23", "input_cost_per_token_batches": 0.000075, "max_tokens": 100000, "output_cost_per_token_batches": 0.0003, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "o1-pro", "model_name": "o1 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 150, "output_cost_per_million": 600, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00015, "output_cost_per_token": 0.0006, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-10-23", "input_cost_per_token_batches": 0.000075, "max_tokens": 100000, "output_cost_per_token_batches": 0.0003, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "o1-pro-2025-03-19", "model_name": "o1 Pro (Mar 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 150, "output_cost_per_million": 600, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00004, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-07-23", "max_tokens": 100000, "source": "https://developers.openai.com/api/docs/models/o3-deep-research", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_pdf_input": true, "model_id": "o3-deep-research", "model_name": "O3 Deep Research", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 10, "output_cost_per_million": 40, "cache_read_cost_per_token": 0.0000025, "cache_read_cost_per_million": 2.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00002, "output_cost_per_token": 0.00008, "max_input_tokens": 200000, "max_output_tokens": 100000, "input_cost_per_token_batches": 0.00001, "max_tokens": 100000, "output_cost_per_token_batches": 0.00004, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o3-pro", "model_name": "o3 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 20, "output_cost_per_million": 80, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00002, "output_cost_per_token": 0.00008, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-12-11", "input_cost_per_token_batches": 0.00001, "max_tokens": 100000, "output_cost_per_token_batches": 0.00004, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o3-pro-2025-06-10", "model_name": "o3 Pro (Jun 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 20, "output_cost_per_million": 80, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-07-23", "max_tokens": 100000, "source": "https://developers.openai.com/api/docs/models/o4-mini-deep-research", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_pdf_input": true, "model_id": "o4-mini-deep-research", "model_name": "O4 Mini Deep Research", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-fable-5", "model_name": "Claude Fable 5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-fable-5-1", "model_name": "Claude Fable 5 1", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "supports_web_search": true, "supports_reasoning": false, "supports_output_config": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-opus-4-5", "model_name": "Claude Opus 4 5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "supports_web_search": true, "supports_reasoning": false, "supports_output_config": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-opus-4-6", "model_name": "Claude Opus 4 6", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "supports_adaptive_thinking": true, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-opus-4-8", "model_name": "Claude Opus 4 8", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "supports_adaptive_thinking": true, "prompt_cache_min_tokens": 512, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-opus-5", "model_name": "Claude Opus 5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000004, "output_cost_per_token": 0.00002, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-opus-5-5", "model_name": "Claude Opus 5 5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "supports_web_search": true, "supports_reasoning": false, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-sonnet-4-5", "model_name": "Claude Sonnet 4 5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-sonnet-4-6", "model_name": "Claude Sonnet 4 6", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "supports_adaptive_thinking": true, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-sonnet-5", "model_name": "Claude Sonnet 5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "supports_adaptive_thinking": true, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-sonnet-5-5", "model_name": "Claude Sonnet 5 5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_web_search": true, "supports_reasoning": false, "model_id": "google/gemini-2.5-pro", "model_name": "Gemini 2.5 Pro", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "supports_web_search": true, "supports_reasoning": false, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3-flash-preview", "model_name": "Gemini 3 Flash Preview", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_web_search": true, "supports_reasoning": false, "model_id": "google/gemini-3-pro-preview", "model_name": "Gemini 3 Pro Preview", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3.1-flash-lite", "model_name": "Gemini 3.1 Flash Lite", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.25, "output_cost_per_million": 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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.000004, "output_cost_per_token_above_200k_tokens": 0.000018, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3.1-pro-preview", "model_name": "Gemini 3.1 Pro Preview", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000009, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3.5-flash", "model_name": "Gemini 3.5 Flash", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3.5-flash-lite", "model_name": "Gemini 3.5 Flash Lite", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000075, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3.6-flash", "model_name": "Gemini 3.6 Flash", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3.7-flash", "model_name": "Gemini 3.7 Flash", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3.8-flash", "model_name": "Gemini 3.8 Flash", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5", "model_name": "GPT-5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "supports_web_search": true, "supports_reasoning": false, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "supports_web_search": true, "supports_reasoning": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.2", "model_name": "GPT-5.2", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "supports_web_search": true, "input_cost_per_token_above_272k_tokens": 0.000005, "output_cost_per_token_above_272k_tokens": 0.0000225, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.4-mini", "model_name": "GPT-5.4 Mini", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.4-nano", "model_name": "GPT-5.4 Nano", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "supports_web_search": true, "input_cost_per_token_above_272k_tokens": 0.00001, "output_cost_per_token_above_272k_tokens": 0.000045, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000012, "supports_web_search": true, "input_cost_per_token_above_272k_tokens": 4e-7, "output_cost_per_token_above_272k_tokens": 0.0000018, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.00002, "supports_web_search": true, "input_cost_per_token_above_272k_tokens": 0.000008, "output_cost_per_token_above_272k_tokens": 0.00003, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.6-sol", "model_name": "GPT-5.6 Sol", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "supports_web_search": true, "input_cost_per_token_above_272k_tokens": 0.000004, "output_cost_per_token_above_272k_tokens": 0.000018, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.6-terra", "model_name": "GPT-5.6 Terra", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 5e-7, "input_cost_per_token_above_272k_tokens": 2e-7, "output_cost_per_token_above_272k_tokens": 7.5e-7, "cache_read_input_token_cost_above_272k_tokens": 2e-8, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-6-luna", "model_name": "GPT-6 Luna", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "input_cost_per_token_above_272k_tokens": 0.000004, "output_cost_per_token_above_272k_tokens": 0.000015, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-6-sol", "model_name": "GPT-6 Sol", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "input_cost_per_token_above_272k_tokens": 0.000004, "output_cost_per_token_above_272k_tokens": 0.000015, "cache_read_input_token_cost_above_272k_tokens": 2e-7, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-6.1-sol", "model_name": "GPT-6.1 Sol", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 10, "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": "responses", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 2.6e-7, "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": true, "model_id": "perplexity/deepseek-v4-flash-0731", "model_name": "Deepseek V4 Flash 0731", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.13, "output_cost_per_million": 0.26, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": true, "model_id": "perplexity/glm-5.2", "model_name": "Glm 5.2", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "perplexity/glm-5.3", "model_name": "Glm 5.3", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 5e-7, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "perplexity/glm-5.3-flash", "model_name": "Glm 5.3 Flash", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.15, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": false, "model_id": "perplexity/kimi-k2.7-code", "model_name": "Kimi K2.7 Code", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.9e-7, "cache_read_cost_per_million": 0.19, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "reasoning_effort_levels": [ "minimal", "low", "medium", "high", "xhigh", "max" ], "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": true, "model_id": "perplexity/kimi-k3", "model_name": "Kimi K3", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000025, "supports_web_search": true, "supports_reasoning": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "perplexity/nemotron-3-ultra-550b-a55b", "model_name": "Nemotron 3 Ultra 550B A55B", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.15e-8, "output_cost_per_token": 1.7e-7, "supports_web_search": true, "supports_reasoning": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "perplexity/nemotron-3.5-lightning-30b-a3b", "model_name": "Nemotron 3.5 Lightning 30B A3B", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.0115, "output_cost_per_million": 0.16999999999999998, "cache_read_cost_per_token": 1.15e-9, "cache_read_cost_per_million": 0.00115, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000025, "supports_web_search": true, "supports_reasoning": false, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "perplexity/sonar", "model_name": "Sonar", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 6.25e-8, "cache_read_cost_per_million": 0.0625, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_web_search": true, "model_id": "preset/advanced-deep-research", "model_name": "Advanced Deep Research", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_web_search": true, "model_id": "preset/deep-research", "model_name": "Deep Research", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_web_search": true, "model_id": "preset/fast-search", "model_name": "Fast Search", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_web_search": true, "model_id": "preset/pro-search", "model_name": "Pro Search", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_web_search": true, "supports_reasoning": false, "model_id": "xai/grok-4-1-fast-non-reasoning", "model_name": "Grok 4 1 Fast Non Reasoning", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "xai/grok-4.20-multi-agent", "model_name": "Grok 4.20 Multi Agent", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "xai/grok-4.20-non-reasoning", "model_name": "Grok 4.20 Non Reasoning", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "xai/grok-4.20-reasoning", "model_name": "Grok 4.20 Reasoning", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "xai/grok-4.3", "model_name": "Grok 4.3", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.000004, "output_cost_per_token_above_200k_tokens": 0.000012, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "xai/grok-4.5", "model_name": "Grok 4.5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.000004, "output_cost_per_token_above_200k_tokens": 0.000012, "cache_read_input_token_cost_above_200k_tokens": 0.000001, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "xai/grok-4.6", "model_name": "Grok 4.6", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supported_endpoints": [ "/v1/responses" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "input_cost_per_image_token": 0.00000125, "model_id": "grok-4.20-multi-agent", "model_name": "Grok 4.20 Multi Agent", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "input_cost_per_image_token": 0.00000125, "supported_endpoints": [ "/v1/responses" ], "model_id": "grok-4.20-multi-agent-0309", "model_name": "Grok 4.20 Multi Agent (Sep 2003)", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supported_endpoints": [ "/v1/responses" ], "model_id": "grok-4.20-multi-agent-beta-0309", "model_name": "Grok 4.20 Multi Agent Beta (Sep 2003)", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supported_endpoints": [ "/v1/responses" ], "model_id": "grok-4.20-multi-agent-beta-latest", "model_name": "Grok 4.20 Multi Agent Beta Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supported_endpoints": [ "/v1/responses" ], "model_id": "grok-4.20-multi-agent-experimental-beta-0304", "model_name": "Grok 4.20 Multi Agent Experimental Beta (Apr 2003)", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supported_endpoints": [ "/v1/responses" ], "model_id": "grok-4.20-multi-agent-experimental-beta-latest", "model_name": "Grok 4.20 Multi Agent Experimental Beta Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supported_endpoints": [ "/v1/responses" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "input_cost_per_image_token": 0.00000125, "model_id": "grok-4.20-multi-agent-latest", "model_name": "Grok 4.20 Multi Agent Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false } ]