diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 02adbbed736..1d863977e1e 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -3144,6 +3144,7 @@ "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3535,6 +3536,7 @@ "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3567,7 +3569,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4172,12 +4174,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4188,13 +4193,17 @@ "azure/eu/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4205,12 +4214,14 @@ "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4351,8 +4362,9 @@ }, "azure/eu/gpt-5.1": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, @@ -4383,12 +4395,17 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.4e-07, + "cache_read_input_token_cost": 1.375e-07, "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.38e-06, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -4419,18 +4436,20 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4454,7 +4473,7 @@ }, "azure/eu/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 2.8e-08, + "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -4462,6 +4481,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4520,12 +4540,15 @@ "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4574,6 +4597,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -4583,12 +4607,15 @@ "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-14", "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4600,12 +4627,15 @@ "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-14", "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4631,12 +4661,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4648,12 +4681,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4664,6 +4700,7 @@ "azure/global/gpt-5.1": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -4695,7 +4732,12 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -4731,7 +4773,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -4743,6 +4786,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4774,6 +4818,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5006,8 +5051,10 @@ "azure/gpt-4.1": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5015,6 +5062,8 @@ "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5040,8 +5089,10 @@ "azure/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5049,6 +5100,8 @@ "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5074,8 +5127,10 @@ "azure/gpt-4.1-mini": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_priority": 7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5083,6 +5138,8 @@ "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, + "output_cost_per_token_priority": 2.8e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5108,8 +5165,10 @@ "azure/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_priority": 7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5117,6 +5176,8 @@ "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, + "output_cost_per_token_priority": 2.8e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5151,6 +5212,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5184,6 +5246,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5243,12 +5306,15 @@ "azure/gpt-4o-2024-05-13": { "deprecation_date": "2026-10-01", "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5259,12 +5325,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5275,13 +5344,16 @@ "azure/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, - "input_cost_per_token": 2.75e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1.1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5468,13 +5540,16 @@ "azure/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, "deprecation_date": "2027-04-14", - "input_cost_per_token": 1.65e-07, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6.6e-07, + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5925,6 +6000,9 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_minimal_reasoning_effort": true }, "azure/gpt-5.1-chat-2025-11-13": { @@ -5963,7 +6041,8 @@ "supports_tool_choice": false, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-codex-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, @@ -5978,6 +6057,7 @@ "mode": "responses", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6012,6 +6092,7 @@ "mode": "responses", "output_cost_per_token": 2e-06, "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6036,13 +6117,19 @@ "azure/gpt-5": { "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6068,14 +6155,20 @@ }, "azure/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2027-02-09", "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6109,7 +6202,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6176,6 +6269,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6200,13 +6294,19 @@ "azure/gpt-5-mini": { "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, + "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6232,14 +6332,20 @@ }, "azure/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2027-02-09", "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, + "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6267,12 +6373,15 @@ "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 5e-09, "input_cost_per_token": 5e-08, + "input_cost_per_token_batches": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6300,12 +6409,15 @@ "cache_read_input_token_cost": 5e-09, "deprecation_date": "2027-02-09", "input_cost_per_token": 5e-08, + "input_cost_per_token_batches": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6332,13 +6444,15 @@ "azure/gpt-5-pro": { "deprecation_date": "2027-04-07", "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00012, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5", + "output_cost_per_token_batches": 6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6362,6 +6476,7 @@ "azure/gpt-5.1": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -6393,7 +6508,12 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -6429,7 +6549,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -6441,6 +6562,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6472,6 +6594,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6503,6 +6626,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6527,13 +6651,19 @@ "azure/gpt-5.2": { "deprecation_date": "2027-06-08", "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, + "input_cost_per_token_batches": 8.75e-07, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_batches": 7e-06, + "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6563,6 +6693,7 @@ "cache_read_input_token_cost_priority": 3.5e-07, "deprecation_date": "2027-06-08", "input_cost_per_token": 1.75e-06, + "input_cost_per_token_batches": 8.75e-07, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -6570,7 +6701,9 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6608,6 +6741,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6643,6 +6777,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6675,6 +6810,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6709,6 +6845,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6733,14 +6870,18 @@ }, "azure/gpt-5.3-codex": { "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "deprecation_date": "2027-08-24", "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6764,17 +6905,20 @@ }, "azure/gpt-5.2-pro": { "input_cost_per_token": 2.1e-05, + "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, + "output_cost_per_token_batches": 8.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -6800,17 +6944,20 @@ }, "azure/gpt-5.2-pro-2025-12-11": { "input_cost_per_token": 2.1e-05, + "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, + "output_cost_per_token_batches": 8.4e-05, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -6838,6 +6985,7 @@ "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "input_cost_per_token": 2.5e-06, @@ -6877,12 +7025,20 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, + "output_cost_per_token_flex": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/us/gpt-5.4": { "deprecation_date": "2027-09-02", - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, @@ -6917,12 +7073,18 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/eu/gpt-5.4": { "deprecation_date": "2027-09-02", - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, @@ -6957,12 +7119,18 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "deprecation_date": "2027-09-02", @@ -7003,11 +7171,19 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, + "output_cost_per_token_flex": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/us/gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "deprecation_date": "2027-09-02", "input_cost_per_token": 2.75e-06, @@ -7043,11 +7219,17 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/eu/gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "deprecation_date": "2027-09-02", "input_cost_per_token": 2.75e-06, @@ -7083,6 +7265,11 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7092,6 +7279,9 @@ "cache_read_input_token_cost_above_272k_tokens": 6e-06, "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_above_272k_tokens_flex": 3e-05, + "input_cost_per_token_batches": 1.5e-05, + "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -7099,11 +7289,15 @@ "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, + "output_cost_per_token_above_272k_tokens_flex": 0.000135, + "output_cost_per_token_batches": 9e-05, + "output_cost_per_token_flex": 9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -7133,6 +7327,9 @@ "deprecation_date": "2027-09-07", "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_above_272k_tokens_flex": 3e-05, + "input_cost_per_token_batches": 1.5e-05, + "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -7140,11 +7337,15 @@ "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, + "output_cost_per_token_above_272k_tokens_flex": 0.000135, + "output_cost_per_token_batches": 9e-05, + "output_cost_per_token_flex": 9e-05, "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'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -7223,33 +7424,42 @@ "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-sol": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_creation_input_token_cost_priority": 1.25e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.5e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_flex": 2.5e-06, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "cache_read_input_token_cost_flex": 2e-07, "deprecation_date": "2028-01-11", - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_above_272k_tokens_flex": 4e-06, + "input_cost_per_token_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, + "input_cost_per_token_flex": 2e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, - "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, + "output_cost_per_token_priority": 4e-05, + "output_cost_per_token_above_272k_tokens_priority": 6e-05, + "output_cost_per_token_flex": 1e-05, "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'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7280,17 +7490,23 @@ "azure/gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_priority": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_flex": 1.25e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, "cache_read_input_token_cost_priority": 4e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_flex": 1e-07, "deprecation_date": "2028-01-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, "input_cost_per_token_priority": 4e-06, "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_flex": 1e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7298,13 +7514,16 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_above_272k_tokens_flex": 9e-06, "output_cost_per_token_priority": 2.4e-05, "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, + "output_cost_per_token_flex": 6e-06, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7335,17 +7554,23 @@ "azure/gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_priority": 5e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, + "cache_creation_input_token_cost_flex": 1.25e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, "cache_read_input_token_cost_priority": 4e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2028-01-11", "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_above_272k_tokens_flex": 2e-07, "input_cost_per_token_priority": 4e-07, "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "input_cost_per_token_flex": 1e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7353,13 +7578,16 @@ "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_above_272k_tokens_flex": 9e-07, "output_cost_per_token_priority": 2.4e-06, "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, + "output_cost_per_token_flex": 6e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7406,6 +7634,7 @@ "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'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -7563,33 +7792,34 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-sol": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05, - "cache_creation_input_token_cost_priority": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06, - "cache_read_input_token_cost_priority": 1.1e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, "deprecation_date": "2028-01-11", - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2.2e-05, - "input_cost_per_token_priority": 1.1e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_above_272k_tokens_priority": 9.9e-05, - "output_cost_per_token_priority": 6.6e-05, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, + "output_cost_per_token_priority": 4.4e-05, "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'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7645,6 +7875,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7700,6 +7931,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7746,6 +7978,7 @@ "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'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -7866,33 +8099,34 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-sol": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05, - "cache_creation_input_token_cost_priority": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06, - "cache_read_input_token_cost_priority": 1.1e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, "deprecation_date": "2028-01-11", - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2.2e-05, - "input_cost_per_token_priority": 1.1e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_above_272k_tokens_priority": 9.9e-05, - "output_cost_per_token_priority": 6.6e-05, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, + "output_cost_per_token_priority": 4.4e-05, "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'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7948,6 +8182,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8003,6 +8238,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8034,12 +8270,16 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "input_cost_per_token_batches": 2.5e-06, + "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -8047,13 +8287,15 @@ "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "output_cost_per_token_batches": 1.5e-05, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8085,9 +8327,10 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, @@ -8097,11 +8340,13 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8133,9 +8378,10 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, @@ -8145,11 +8391,13 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 1.65e-05, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8180,11 +8428,12 @@ "azure/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure", "max_input_tokens": 1050000, @@ -8193,7 +8442,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -8223,12 +8472,17 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2027-10-26" + "deprecation_date": "2027-10-26", + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "input_cost_per_token_flex": 2.5e-06, + "output_cost_per_token_batches": 1.5e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, @@ -8268,12 +8522,15 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2027-10-26" + "deprecation_date": "2027-10-26", + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.65e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, @@ -8313,7 +8570,10 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2027-10-26" + "deprecation_date": "2027-10-26", + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.65e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, @@ -8402,6 +8662,8 @@ "azure/gpt-5.4-mini": { "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -8439,10 +8701,19 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.5e-06, + "output_cost_per_token_batches": 2.25e-06, + "output_cost_per_token_flex": 2.25e-06, + "output_cost_per_token_priority": 9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-mini-2026-03-17": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.5e-07, "deprecation_date": "2027-09-21", "input_cost_per_token": 7.5e-07, "litellm_provider": "azure", @@ -8481,11 +8752,19 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.5e-06, + "output_cost_per_token_batches": 2.25e-06, + "output_cost_per_token_flex": 2.25e-06, + "output_cost_per_token_priority": 9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano": { "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_flex": 1e-08, "input_cost_per_token": 2e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -8523,10 +8802,16 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "output_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_flex": 6.25e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano-2026-03-17": { "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2027-09-21", "input_cost_per_token": 2e-07, "litellm_provider": "azure", @@ -8565,6 +8850,11 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "output_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_flex": 6.25e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-image-1": { @@ -8886,12 +9176,15 @@ "cache_read_input_token_cost": 7.5e-06, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, + "output_cost_per_token_batches": 3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -8900,14 +9193,17 @@ "supports_vision": true }, "azure/o1-mini": { - "cache_read_input_token_cost": 6.05e-07, - "input_cost_per_token": 1.21e-06, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 4.84e-06, + "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -8938,6 +9234,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -8953,6 +9250,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -8994,12 +9292,15 @@ "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9035,6 +9336,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9078,12 +9380,15 @@ "cache_read_input_token_cost": 5.5e-07, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -9100,6 +9405,7 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9131,6 +9437,7 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9185,12 +9492,15 @@ "cache_read_input_token_cost": 2.75e-07, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -9230,7 +9540,8 @@ "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/text-embedding-3-small": { "deprecation_date": "2028-02-09", @@ -9239,7 +9550,8 @@ "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/text-embedding-ada-002": { "deprecation_date": "2028-02-09", @@ -9248,7 +9560,8 @@ "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/speech/azure-tts": { "input_cost_per_character": 1.5e-05, @@ -9390,12 +9703,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9406,13 +9722,17 @@ "azure/us/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -9423,12 +9743,14 @@ "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9602,8 +9924,9 @@ }, "azure/us/gpt-5.1": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, @@ -9634,12 +9957,17 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.4e-07, + "cache_read_input_token_cost": 1.375e-07, "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.38e-06, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -9670,18 +9998,20 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -9705,7 +10035,7 @@ }, "azure/us/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 2.8e-08, + "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -9713,6 +10043,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -9738,12 +10069,15 @@ "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9784,12 +10118,15 @@ "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9822,21 +10159,25 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "azure/us/o4-mini-2025-04-16": { - "cache_read_input_token_cost": 3.1e-07, + "cache_read_input_token_cost": 3.03e-07, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -9882,7 +10223,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], @@ -9931,7 +10272,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9946,7 +10287,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.828e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9962,7 +10303,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.52e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9978,7 +10319,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9993,37 +10334,37 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-GLM-5.2-Fast": { - "cache_read_input_token_cost": 2.1e-07, - "input_cost_per_token": 2.1e-06, + "cache_read_input_token_cost": 2.31e-07, + "input_cost_per_token": 2.31e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 6.6e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token": 7.26e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-Inkling": { - "cache_read_input_token_cost": 1.7e-07, - "input_cost_per_token": 1e-06, + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 1.1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 4.05e-06, - "source": "https://fireworks.ai/models/fireworks/inkling", + "output_cost_per_token": 4.46e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10045,7 +10386,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.3e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10068,7 +10409,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10091,7 +10432,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10119,7 +10460,7 @@ "high", "max" ], - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k3-through-fireworks-ai-on-microsoft-foundry/4540187", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10143,7 +10484,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10158,7 +10499,7 @@ "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10179,7 +10520,7 @@ "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10193,15 +10534,15 @@ "supports_vision": false }, "azure_ai/FW-Nemotron-3-Ultra-NVFP4": { - "cache_read_input_token_cost": 1.19e-07, - "input_cost_per_token": 6e-07, + "cache_read_input_token_cost": 1.3e-07, + "input_cost_per_token": 6.6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2.4e-06, - "source": "https://fireworks.ai/models/fireworks/nemotron-3-ultra-nvfp4", + "output_cost_per_token": 2.64e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10220,7 +10561,7 @@ "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_image_token": 4.7e-05, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10234,7 +10575,7 @@ "mode": "image_generation", "output_cost_per_image": 0.0338, "output_cost_per_image_token": 3.3e-05, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10248,7 +10589,7 @@ "mode": "image_generation", "output_cost_per_image": 0.02, "output_cost_per_image_token": 1.95e-05, - "source": "https://aka.ms/mai-image-2e-foundryblog", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations" ] @@ -10262,7 +10603,7 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], @@ -10313,19 +10654,19 @@ "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 7.1e-07, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "input_cost_per_token": 1.41e-06, + "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 3.5e-07, - "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", + "output_cost_per_token": 1e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -10396,7 +10737,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10408,7 +10749,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10420,7 +10761,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10432,7 +10773,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10444,7 +10785,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10456,7 +10797,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10468,7 +10809,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.4e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10480,7 +10821,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10492,7 +10833,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": true }, @@ -10504,7 +10845,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": false @@ -10517,7 +10858,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-multimodal-instruct": { @@ -10529,20 +10870,20 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-07, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_audio_input": true, "supports_function_calling": true, "supports_vision": true }, "azure_ai/Phi-4-mini-reasoning": { - "input_cost_per_token": 8e-08, + "input_cost_per_token": 7.5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "output_cost_per_token": 3e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-reasoning": { @@ -10553,7 +10894,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true @@ -10605,7 +10946,7 @@ "max_tokens": 8182, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/cohere/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, @@ -10644,7 +10985,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true, "supports_tool_choice": true }, @@ -10709,7 +11050,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -10724,7 +11065,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -10740,7 +11081,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true, "supports_tool_choice": true }, @@ -10752,7 +11093,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true }, "azure_ai/deepseek-v3-0324": { @@ -10764,7 +11105,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, @@ -10777,7 +11118,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.94e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true @@ -10791,7 +11132,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -10807,7 +11148,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 5.1e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -10824,7 +11165,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10838,7 +11179,7 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 3072, - "source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/embeddings" ], @@ -10857,7 +11198,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, @@ -10872,7 +11213,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.27e-06, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, @@ -10888,7 +11229,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, @@ -10903,7 +11244,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.27e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, @@ -10918,7 +11259,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -10933,7 +11274,7 @@ "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-grok-4-3-on-microsoft-foundry-latest-generation-agentic-capabilities/4517096", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10951,7 +11292,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/grok-4-6-comes-to-microsoft-foundry-models-built-for-long-horizon-reasoning-and-/4547578", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10970,7 +11311,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -10988,7 +11329,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11004,6 +11345,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11018,7 +11360,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11032,7 +11374,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11046,7 +11388,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -11061,7 +11403,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11096,7 +11438,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_video_input": true, @@ -11113,7 +11455,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -11183,7 +11525,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://azure.microsoft.com/en-us/blog/introducing-mistral-large-3-in-microsoft-foundry-open-capable-and-ready-for-production-workloads/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -61814,7 +62156,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -66133,5 +66475,586 @@ "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://api.together.ai/v1/models" + }, + "azure/eu/codex-mini": { + "cache_read_input_token_cost": 4.13e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/computer-use-preview": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.32e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1-mini": { + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, + "input_cost_per_token": 4.4e-07, + "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.76e-06, + "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_batches": 5.5e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4o-2024-05-13": { + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5": { + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-codex": { + "cache_read_input_token_cost": 1.38e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-mini": { + "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, + "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-nano": { + "cache_read_input_token_cost": 5.5e-09, + "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-pro": { + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000132, + "output_cost_per_token_batches": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.1-codex-max": { + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_batches": 9.625e-07, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_batches": 7.7e-06, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2-codex": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2-pro": { + "input_cost_per_token": 2.31e-05, + "input_cost_per_token_batches": 1.155e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0001848, + "output_cost_per_token_batches": 9.24e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.3-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-mini": { + "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_priority": 1.65e-07, + "input_cost_per_token": 8.25e-07, + "input_cost_per_token_batches": 4.125e-07, + "input_cost_per_token_priority": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.95e-06, + "output_cost_per_token_batches": 2.475e-06, + "output_cost_per_token_priority": 9.9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-nano": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.375e-06, + "output_cost_per_token_batches": 6.875e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-pro": { + "input_cost_per_token": 3.3e-05, + "input_cost_per_token_above_272k_tokens": 6.6e-05, + "input_cost_per_token_batches": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000198, + "output_cost_per_token_above_272k_tokens": 0.000297, + "output_cost_per_token_batches": 9.9e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-6-astra": { + "cache_creation_input_token_cost": 1.375e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, + "cache_read_input_token_cost": 1.1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, + "input_cost_per_token": 1.1e-05, + "input_cost_per_token_above_272k_tokens": 2.2e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 5.5e-05, + "output_cost_per_token_above_272k_tokens": 8.25e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o1-preview": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o3-2025-04-16": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o3-deep-research": { + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o4-mini-2025-04-16": { + "cache_read_input_token_cost": 3.03e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-3-large": { + "input_cost_per_token": 1.43e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-3-small": { + "input_cost_per_token": 2.2e-08, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-ada-002": { + "input_cost_per_token": 1.1e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "gemini/gemini-3.8-live": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": true + }, + "gemini/gemini-3.8-live-extended-thinking": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": true + }, + "azure/us/codex-mini": { + "cache_read_input_token_cost": 4.13e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/computer-use-preview": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.32e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1-mini": { + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, + "input_cost_per_token": 4.4e-07, + "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.76e-06, + "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_batches": 5.5e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4o-2024-05-13": { + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5": { + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-codex": { + "cache_read_input_token_cost": 1.38e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-mini": { + "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, + "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-nano": { + "cache_read_input_token_cost": 5.5e-09, + "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-pro": { + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000132, + "output_cost_per_token_batches": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.1-codex-max": { + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_batches": 9.625e-07, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_batches": 7.7e-06, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-codex": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-pro": { + "input_cost_per_token": 2.31e-05, + "input_cost_per_token_batches": 1.155e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0001848, + "output_cost_per_token_batches": 9.24e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.3-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-mini": { + "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_priority": 1.65e-07, + "input_cost_per_token": 8.25e-07, + "input_cost_per_token_batches": 4.125e-07, + "input_cost_per_token_priority": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.95e-06, + "output_cost_per_token_batches": 2.475e-06, + "output_cost_per_token_priority": 9.9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-nano": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.375e-06, + "output_cost_per_token_batches": 6.875e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-pro": { + "input_cost_per_token": 3.3e-05, + "input_cost_per_token_above_272k_tokens": 6.6e-05, + "input_cost_per_token_batches": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000198, + "output_cost_per_token_above_272k_tokens": 0.000297, + "output_cost_per_token_batches": 9.9e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o1-preview": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o3-deep-research": { + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-3-large": { + "input_cost_per_token": 1.43e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-3-small": { + "input_cost_per_token": 2.2e-08, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-ada-002": { + "input_cost_per_token": 1.1e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 02adbbed736..1d863977e1e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -3144,6 +3144,7 @@ "max_tokens": 100000, "mode": "responses", "output_cost_per_token": 6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3535,6 +3536,7 @@ "max_tokens": 1024, "mode": "chat", "output_cost_per_token": 1.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -3567,7 +3569,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4172,12 +4174,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4188,13 +4193,17 @@ "azure/eu/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4205,12 +4214,14 @@ "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4351,8 +4362,9 @@ }, "azure/eu/gpt-5.1": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, @@ -4383,12 +4395,17 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.4e-07, + "cache_read_input_token_cost": 1.375e-07, "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.38e-06, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -4419,18 +4436,20 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4454,7 +4473,7 @@ }, "azure/eu/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 2.8e-08, + "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -4462,6 +4481,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4520,12 +4540,15 @@ "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4574,6 +4597,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -4583,12 +4607,15 @@ "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-14", "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4600,12 +4627,15 @@ "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-04-14", "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -4631,12 +4661,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4648,12 +4681,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4664,6 +4700,7 @@ "azure/global/gpt-5.1": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -4695,7 +4732,12 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -4731,7 +4773,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/global/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -4743,6 +4786,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -4774,6 +4818,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -5006,8 +5051,10 @@ "azure/gpt-4.1": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5015,6 +5062,8 @@ "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5040,8 +5089,10 @@ "azure/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5049,6 +5100,8 @@ "mode": "chat", "output_cost_per_token": 8e-06, "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5074,8 +5127,10 @@ "azure/gpt-4.1-mini": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_priority": 7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5083,6 +5138,8 @@ "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, + "output_cost_per_token_priority": 2.8e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5108,8 +5165,10 @@ "azure/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_priority": 1.75e-07, "input_cost_per_token": 4e-07, "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_priority": 7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -5117,6 +5176,8 @@ "mode": "chat", "output_cost_per_token": 1.6e-06, "output_cost_per_token_batches": 8e-07, + "output_cost_per_token_priority": 2.8e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5151,6 +5212,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5184,6 +5246,7 @@ "mode": "chat", "output_cost_per_token": 4e-07, "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -5243,12 +5306,15 @@ "azure/gpt-4o-2024-05-13": { "deprecation_date": "2026-10-01", "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5259,12 +5325,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5275,13 +5344,16 @@ "azure/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, - "input_cost_per_token": 2.75e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 1.1e-05, + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5468,13 +5540,16 @@ "azure/gpt-4o-mini-2024-07-18": { "cache_read_input_token_cost": 7.5e-08, "deprecation_date": "2027-04-14", - "input_cost_per_token": 1.65e-07, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 6.6e-07, + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -5925,6 +6000,9 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_batches": 5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_minimal_reasoning_effort": true }, "azure/gpt-5.1-chat-2025-11-13": { @@ -5963,7 +6041,8 @@ "supports_tool_choice": false, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-codex-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, @@ -5978,6 +6057,7 @@ "mode": "responses", "output_cost_per_token": 1e-05, "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6012,6 +6092,7 @@ "mode": "responses", "output_cost_per_token": 2e-06, "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6036,13 +6117,19 @@ "azure/gpt-5": { "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6068,14 +6155,20 @@ }, "azure/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "deprecation_date": "2027-02-09", "input_cost_per_token": 1.25e-06, + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6109,7 +6202,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6176,6 +6269,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6200,13 +6294,19 @@ "azure/gpt-5-mini": { "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, + "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6232,14 +6332,20 @@ }, "azure/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, "deprecation_date": "2027-02-09", "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06, + "output_cost_per_token_priority": 3.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6267,12 +6373,15 @@ "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 5e-09, "input_cost_per_token": 5e-08, + "input_cost_per_token_batches": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6300,12 +6409,15 @@ "cache_read_input_token_cost": 5e-09, "deprecation_date": "2027-02-09", "input_cost_per_token": 5e-08, + "input_cost_per_token_batches": 2.5e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6332,13 +6444,15 @@ "azure/gpt-5-pro": { "deprecation_date": "2027-04-07", "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.00012, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5", + "output_cost_per_token_batches": 6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6362,6 +6476,7 @@ "azure/gpt-5.1": { "deprecation_date": "2027-05-15", "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_priority": 2.5e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -6393,7 +6508,12 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -6429,7 +6549,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.1-codex": { "deprecation_date": "2027-05-15", @@ -6441,6 +6562,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6472,6 +6594,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6503,6 +6626,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6527,13 +6651,19 @@ "azure/gpt-5.2": { "deprecation_date": "2027-06-08", "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "input_cost_per_token": 1.75e-06, + "input_cost_per_token_batches": 8.75e-07, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_batches": 7e-06, + "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6563,6 +6693,7 @@ "cache_read_input_token_cost_priority": 3.5e-07, "deprecation_date": "2027-06-08", "input_cost_per_token": 1.75e-06, + "input_cost_per_token_batches": 8.75e-07, "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -6570,7 +6701,9 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_batches": 7e-06, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -6608,6 +6741,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6643,6 +6777,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6675,6 +6810,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6709,6 +6845,7 @@ "mode": "chat", "output_cost_per_token": 1.4e-05, "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -6733,14 +6870,18 @@ }, "azure/gpt-5.3-codex": { "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, "deprecation_date": "2027-08-24", "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -6764,17 +6905,20 @@ }, "azure/gpt-5.2-pro": { "input_cost_per_token": 2.1e-05, + "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, + "output_cost_per_token_batches": 8.4e-05, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -6800,17 +6944,20 @@ }, "azure/gpt-5.2-pro-2025-12-11": { "input_cost_per_token": 2.1e-05, + "input_cost_per_token_batches": 1.05e-05, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 0.000168, + "output_cost_per_token_batches": 8.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -6838,6 +6985,7 @@ "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "input_cost_per_token": 2.5e-06, @@ -6877,12 +7025,20 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, + "output_cost_per_token_flex": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/us/gpt-5.4": { "deprecation_date": "2027-09-02", - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, @@ -6917,12 +7073,18 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/eu/gpt-5.4": { "deprecation_date": "2027-09-02", - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "input_cost_per_token": 2.75e-06, "input_cost_per_token_priority": 5.5e-06, @@ -6957,12 +7119,18 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.5e-07, "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_read_input_token_cost_priority": 5e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "deprecation_date": "2027-09-02", @@ -7003,11 +7171,19 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens_flex": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_above_272k_tokens_flex": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, + "output_cost_per_token_flex": 7.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/us/gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "deprecation_date": "2027-09-02", "input_cost_per_token": 2.75e-06, @@ -7043,11 +7219,17 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, "azure/eu/gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.8e-07, + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_above_272k_tokens": 5.5e-07, "cache_read_input_token_cost_priority": 5.5e-07, "deprecation_date": "2027-09-02", "input_cost_per_token": 2.75e-06, @@ -7083,6 +7265,11 @@ "supports_vision": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_above_272k_tokens": 5.5e-06, + "input_cost_per_token_batches": 1.375e-06, + "output_cost_per_token_above_272k_tokens": 2.475e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true }, @@ -7092,6 +7279,9 @@ "cache_read_input_token_cost_above_272k_tokens": 6e-06, "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_above_272k_tokens_flex": 3e-05, + "input_cost_per_token_batches": 1.5e-05, + "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -7099,11 +7289,15 @@ "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, + "output_cost_per_token_above_272k_tokens_flex": 0.000135, + "output_cost_per_token_batches": 9e-05, + "output_cost_per_token_flex": 9e-05, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -7133,6 +7327,9 @@ "deprecation_date": "2027-09-07", "input_cost_per_token": 3e-05, "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_above_272k_tokens_flex": 3e-05, + "input_cost_per_token_batches": 1.5e-05, + "input_cost_per_token_flex": 1.5e-05, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -7140,11 +7337,15 @@ "mode": "responses", "output_cost_per_token": 0.00018, "output_cost_per_token_above_272k_tokens": 0.00027, + "output_cost_per_token_above_272k_tokens_flex": 0.000135, + "output_cost_per_token_batches": 9e-05, + "output_cost_per_token_flex": 9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" @@ -7223,33 +7424,42 @@ "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-sol": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_creation_input_token_cost_priority": 1.25e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.5e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_flex": 2.5e-06, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "cache_read_input_token_cost_flex": 2e-07, "deprecation_date": "2028-01-11", - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_above_272k_tokens_flex": 4e-06, + "input_cost_per_token_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, + "input_cost_per_token_flex": 2e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, - "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, + "output_cost_per_token_priority": 4e-05, + "output_cost_per_token_above_272k_tokens_priority": 6e-05, + "output_cost_per_token_flex": 1e-05, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7280,17 +7490,23 @@ "azure/gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, "cache_creation_input_token_cost_priority": 5e-06, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_flex": 1.25e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, "cache_read_input_token_cost_priority": 4e-07, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_flex": 1e-07, "deprecation_date": "2028-01-11", "input_cost_per_token": 2e-06, "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, "input_cost_per_token_priority": 4e-06, "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_flex": 1e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7298,13 +7514,16 @@ "mode": "chat", "output_cost_per_token": 1.2e-05, "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_above_272k_tokens_flex": 9e-06, "output_cost_per_token_priority": 2.4e-05, "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, + "output_cost_per_token_flex": 6e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7335,17 +7554,23 @@ "azure/gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_priority": 5e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, + "cache_creation_input_token_cost_flex": 1.25e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, "cache_read_input_token_cost_priority": 4e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2028-01-11", "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_above_272k_tokens_flex": 2e-07, "input_cost_per_token_priority": 4e-07, "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "input_cost_per_token_flex": 1e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7353,13 +7578,16 @@ "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_above_272k_tokens_flex": 9e-07, "output_cost_per_token_priority": 2.4e-06, "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, + "output_cost_per_token_flex": 6e-07, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7406,6 +7634,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -7563,33 +7792,34 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-sol": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05, - "cache_creation_input_token_cost_priority": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06, - "cache_read_input_token_cost_priority": 1.1e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, "deprecation_date": "2028-01-11", - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2.2e-05, - "input_cost_per_token_priority": 1.1e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_above_272k_tokens_priority": 9.9e-05, - "output_cost_per_token_priority": 6.6e-05, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, + "output_cost_per_token_priority": 4.4e-05, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7645,6 +7875,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7700,6 +7931,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7746,6 +7978,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -7866,33 +8099,34 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-sol": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05, - "cache_creation_input_token_cost_priority": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06, - "cache_read_input_token_cost_priority": 1.1e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, "deprecation_date": "2028-01-11", - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2.2e-05, - "input_cost_per_token_priority": 1.1e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_above_272k_tokens_priority": 9.9e-05, - "output_cost_per_token_priority": 6.6e-05, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, + "output_cost_per_token_priority": 4.4e-05, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7948,6 +8182,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8003,6 +8238,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8034,12 +8270,16 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "input_cost_per_token_batches": 2.5e-06, + "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -8047,13 +8287,15 @@ "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "output_cost_per_token_batches": 1.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8085,9 +8327,10 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, @@ -8097,11 +8340,13 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 1.65e-05, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8133,9 +8378,10 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, @@ -8145,11 +8391,13 @@ "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", + "output_cost_per_token_batches": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -8180,11 +8428,12 @@ "azure/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, "litellm_provider": "azure", "max_input_tokens": 1050000, @@ -8193,7 +8442,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -8223,12 +8472,17 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2027-10-26" + "deprecation_date": "2027-10-26", + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "input_cost_per_token_flex": 2.5e-06, + "output_cost_per_token_batches": 1.5e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, @@ -8268,12 +8522,15 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2027-10-26" + "deprecation_date": "2027-10-26", + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.65e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, @@ -8313,7 +8570,10 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "deprecation_date": "2027-10-26" + "deprecation_date": "2027-10-26", + "input_cost_per_token_batches": 2.75e-06, + "output_cost_per_token_batches": 1.65e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, @@ -8402,6 +8662,8 @@ "azure/gpt-5.4-mini": { "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.5e-07, "input_cost_per_token": 7.5e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -8439,10 +8701,19 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.5e-06, + "output_cost_per_token_batches": 2.25e-06, + "output_cost_per_token_flex": 2.25e-06, + "output_cost_per_token_priority": 9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-mini-2026-03-17": { "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.5e-07, "deprecation_date": "2027-09-21", "input_cost_per_token": 7.5e-07, "litellm_provider": "azure", @@ -8481,11 +8752,19 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.5e-06, + "output_cost_per_token_batches": 2.25e-06, + "output_cost_per_token_flex": 2.25e-06, + "output_cost_per_token_priority": 9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano": { "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_flex": 1e-08, "input_cost_per_token": 2e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -8523,10 +8802,16 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "output_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_flex": 6.25e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-5.4-nano-2026-03-17": { "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2027-09-21", "input_cost_per_token": 2e-07, "litellm_provider": "azure", @@ -8565,6 +8850,11 @@ "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", + "input_cost_per_token_batches": 1e-07, + "input_cost_per_token_flex": 1e-07, + "output_cost_per_token_batches": 6.25e-07, + "output_cost_per_token_flex": 6.25e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true }, "azure/gpt-image-1": { @@ -8886,12 +9176,15 @@ "cache_read_input_token_cost": 7.5e-06, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6e-05, + "output_cost_per_token_batches": 3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -8900,14 +9193,17 @@ "supports_vision": true }, "azure/o1-mini": { - "cache_read_input_token_cost": 6.05e-07, - "input_cost_per_token": 1.21e-06, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 4.84e-06, + "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -8938,6 +9234,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -8953,6 +9250,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_pdf_input": true, @@ -8994,12 +9292,15 @@ "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9035,6 +9336,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9078,12 +9380,15 @@ "cache_read_input_token_cost": 5.5e-07, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -9100,6 +9405,7 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9131,6 +9437,7 @@ "mode": "responses", "output_cost_per_token": 8e-05, "output_cost_per_token_batches": 4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9185,12 +9492,15 @@ "cache_read_input_token_cost": 2.75e-07, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -9230,7 +9540,8 @@ "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/text-embedding-3-small": { "deprecation_date": "2028-02-09", @@ -9239,7 +9550,8 @@ "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/text-embedding-ada-002": { "deprecation_date": "2028-02-09", @@ -9248,7 +9560,8 @@ "max_input_tokens": 8191, "max_tokens": 8191, "mode": "embedding", - "output_cost_per_token": 0.0 + "output_cost_per_token": 0.0, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/speech/azure-tts": { "input_cost_per_character": 1.5e-05, @@ -9390,12 +9703,15 @@ "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9406,13 +9722,17 @@ "azure/us/gpt-4o-2024-11-20": { "deprecation_date": "2027-04-14", "cache_creation_input_token_cost": 1.38e-06, + "cache_read_input_token_cost": 1.375e-06, "input_cost_per_token": 2.75e-06, + "input_cost_per_token_batches": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -9423,12 +9743,14 @@ "cache_read_input_token_cost": 8.3e-08, "deprecation_date": "2027-04-14", "input_cost_per_token": 1.65e-07, + "input_cost_per_token_batches": 8.3e-08, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 6.6e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9602,8 +9924,9 @@ }, "azure/us/gpt-5.1": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, @@ -9634,12 +9957,17 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-chat": { - "cache_read_input_token_cost": 1.4e-07, + "cache_read_input_token_cost": 1.375e-07, "deprecation_date": "2026-06-29", - "input_cost_per_token": 1.38e-06, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -9670,18 +9998,20 @@ "supports_tool_choice": true, "supports_vision": true, "supports_none_reasoning_effort": true, - "default_reasoning_effort": "none" + "default_reasoning_effort": "none", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 1.4e-07, - "input_cost_per_token": 1.38e-06, + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -9705,7 +10035,7 @@ }, "azure/us/gpt-5.1-codex-mini": { "deprecation_date": "2027-05-15", - "cache_read_input_token_cost": 2.8e-08, + "cache_read_input_token_cost": 2.75e-08, "input_cost_per_token": 2.75e-07, "litellm_provider": "azure", "max_input_tokens": 272000, @@ -9713,6 +10043,7 @@ "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/responses" ], @@ -9738,12 +10069,15 @@ "cache_read_input_token_cost": 8.25e-06, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 6.6e-05, + "output_cost_per_token_batches": 3.3e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9784,12 +10118,15 @@ "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9822,21 +10159,25 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_vision": false }, "azure/us/o4-mini-2025-04-16": { - "cache_read_input_token_cost": 3.1e-07, + "cache_read_input_token_cost": 3.03e-07, "deprecation_date": "2026-11-19", "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "mode": "chat", "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_prompt_caching": true, @@ -9882,7 +10223,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 9e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/mistral/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], @@ -9931,7 +10272,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.85e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9946,7 +10287,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.828e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9962,7 +10303,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.52e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9978,7 +10319,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -9993,37 +10334,37 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.84e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-GLM-5.2-Fast": { - "cache_read_input_token_cost": 2.1e-07, - "input_cost_per_token": 2.1e-06, + "cache_read_input_token_cost": 2.31e-07, + "input_cost_per_token": 2.31e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 6.6e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "output_cost_per_token": 7.26e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true }, "azure_ai/FW-Inkling": { - "cache_read_input_token_cost": 1.7e-07, - "input_cost_per_token": 1e-06, + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 1.1e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 1048576, "max_tokens": 1048576, "mode": "chat", - "output_cost_per_token": 4.05e-06, - "source": "https://fireworks.ai/models/fireworks/inkling", + "output_cost_per_token": 4.46e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10045,7 +10386,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3.3e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10068,7 +10409,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10091,7 +10432,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4.4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10119,7 +10460,7 @@ "high", "max" ], - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k3-through-fireworks-ai-on-microsoft-foundry/4540187", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10143,7 +10484,7 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10158,7 +10499,7 @@ "max_tokens": 512000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -10179,7 +10520,7 @@ "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/fireworks/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10193,15 +10534,15 @@ "supports_vision": false }, "azure_ai/FW-Nemotron-3-Ultra-NVFP4": { - "cache_read_input_token_cost": 1.19e-07, - "input_cost_per_token": 6e-07, + "cache_read_input_token_cost": 1.3e-07, + "input_cost_per_token": 6.6e-07, "litellm_provider": "azure_ai", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 2.4e-06, - "source": "https://fireworks.ai/models/fireworks/nemotron-3-ultra-nvfp4", + "output_cost_per_token": 2.64e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text" ], @@ -10220,7 +10561,7 @@ "mode": "image_generation", "output_cost_per_image": 0.05, "output_cost_per_image_token": 4.7e-05, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10234,7 +10575,7 @@ "mode": "image_generation", "output_cost_per_image": 0.0338, "output_cost_per_image_token": 3.3e-05, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" @@ -10248,7 +10589,7 @@ "mode": "image_generation", "output_cost_per_image": 0.02, "output_cost_per_image_token": 1.95e-05, - "source": "https://aka.ms/mai-image-2e-foundryblog", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/images/generations" ] @@ -10262,7 +10603,7 @@ "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 8e-06, - "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions" ], @@ -10313,19 +10654,19 @@ "max_tokens": 2048, "mode": "chat", "output_cost_per_token": 7.1e-07, - "source": "https://marketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "input_cost_per_token": 1.41e-06, + "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", - "output_cost_per_token": 3.5e-07, - "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", + "output_cost_per_token": 1e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -10396,7 +10737,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10408,7 +10749,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.8e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10420,7 +10761,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10432,7 +10773,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10444,7 +10785,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10456,7 +10797,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10468,7 +10809,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 6.4e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10480,7 +10821,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": false }, @@ -10492,7 +10833,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_vision": true }, @@ -10504,7 +10845,7 @@ "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": false @@ -10517,7 +10858,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3e-07, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-multimodal-instruct": { @@ -10529,20 +10870,20 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 3.2e-07, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_audio_input": true, "supports_function_calling": true, "supports_vision": true }, "azure_ai/Phi-4-mini-reasoning": { - "input_cost_per_token": 8e-08, + "input_cost_per_token": 7.5e-08, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "mode": "chat", - "output_cost_per_token": 3.2e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "output_cost_per_token": 3e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true }, "azure_ai/Phi-4-reasoning": { @@ -10553,7 +10894,7 @@ "max_tokens": 4096, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_reasoning": true @@ -10605,7 +10946,7 @@ "max_tokens": 8182, "mode": "chat", "output_cost_per_token": 1e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/cohere/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, @@ -10644,7 +10985,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true, "supports_tool_choice": true }, @@ -10709,7 +11050,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -10724,7 +11065,7 @@ "max_tokens": 163840, "mode": "chat", "output_cost_per_token": 1.68e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -10740,7 +11081,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true, "supports_tool_choice": true }, @@ -10752,7 +11093,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true }, "azure_ai/deepseek-v3-0324": { @@ -10764,7 +11105,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 4.56e-06, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true }, @@ -10777,7 +11118,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 4.94e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true @@ -10791,7 +11132,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 3.48e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -10807,7 +11148,7 @@ "max_tokens": 384000, "mode": "chat", "output_cost_per_token": 5.1e-07, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, @@ -10824,7 +11165,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.32e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10838,7 +11179,7 @@ "mode": "embedding", "output_cost_per_token": 0.0, "output_vector_size": 3072, - "source": "https://marketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/embeddings" ], @@ -10857,7 +11198,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, @@ -10872,7 +11213,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.27e-06, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, @@ -10888,7 +11229,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": false, "supports_tool_choice": true, @@ -10903,7 +11244,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.27e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": false, @@ -10918,7 +11259,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-05, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -10933,7 +11274,7 @@ "max_tokens": 200000, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-grok-4-3-on-microsoft-foundry-latest-generation-agentic-capabilities/4517096", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10951,7 +11292,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 6e-06, - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/grok-4-6-comes-to-microsoft-foundry-models-built-for-long-horizon-reasoning-and-/4547578", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -10970,7 +11311,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -10988,7 +11329,7 @@ "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11004,6 +11345,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11018,7 +11360,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11032,7 +11374,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11046,7 +11388,7 @@ "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -11061,7 +11403,7 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -11096,7 +11438,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 3e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_video_input": true, @@ -11113,7 +11455,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -11183,7 +11525,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://azure.microsoft.com/en-us/blog/introducing-mistral-large-3-in-microsoft-foundry-open-capable-and-ready-for-production-workloads/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -61814,7 +62156,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 4e-06, - "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_modalities": [ "text", "image" @@ -66133,5 +66475,586 @@ "mode": "chat", "output_cost_per_token": 8e-06, "source": "https://api.together.ai/v1/models" + }, + "azure/eu/codex-mini": { + "cache_read_input_token_cost": 4.13e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/computer-use-preview": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.32e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1-mini": { + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, + "input_cost_per_token": 4.4e-07, + "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.76e-06, + "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_batches": 5.5e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-4o-2024-05-13": { + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5": { + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-codex": { + "cache_read_input_token_cost": 1.38e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-mini": { + "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, + "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-nano": { + "cache_read_input_token_cost": 5.5e-09, + "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5-pro": { + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000132, + "output_cost_per_token_batches": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.1-codex-max": { + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_batches": 9.625e-07, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_batches": 7.7e-06, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2-codex": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.2-pro": { + "input_cost_per_token": 2.31e-05, + "input_cost_per_token_batches": 1.155e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0001848, + "output_cost_per_token_batches": 9.24e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.3-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-mini": { + "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_priority": 1.65e-07, + "input_cost_per_token": 8.25e-07, + "input_cost_per_token_batches": 4.125e-07, + "input_cost_per_token_priority": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.95e-06, + "output_cost_per_token_batches": 2.475e-06, + "output_cost_per_token_priority": 9.9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-nano": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.375e-06, + "output_cost_per_token_batches": 6.875e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-5.4-pro": { + "input_cost_per_token": 3.3e-05, + "input_cost_per_token_above_272k_tokens": 6.6e-05, + "input_cost_per_token_batches": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000198, + "output_cost_per_token_above_272k_tokens": 0.000297, + "output_cost_per_token_batches": 9.9e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/gpt-6-astra": { + "cache_creation_input_token_cost": 1.375e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, + "cache_read_input_token_cost": 1.1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, + "input_cost_per_token": 1.1e-05, + "input_cost_per_token_above_272k_tokens": 2.2e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 5.5e-05, + "output_cost_per_token_above_272k_tokens": 8.25e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o1-preview": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o3-2025-04-16": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o3-deep-research": { + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/o4-mini-2025-04-16": { + "cache_read_input_token_cost": 3.03e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-3-large": { + "input_cost_per_token": 1.43e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-3-small": { + "input_cost_per_token": 2.2e-08, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/eu/text-embedding-ada-002": { + "input_cost_per_token": 1.1e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "gemini/gemini-3.8-live": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": true + }, + "gemini/gemini-3.8-live-extended-thinking": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": false, + "supports_vision": true, + "supports_web_search": true + }, + "azure/us/codex-mini": { + "cache_read_input_token_cost": 4.13e-07, + "input_cost_per_token": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/computer-use-preview": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.32e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1": { + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_priority": 9.63e-07, + "input_cost_per_token": 2.2e-06, + "input_cost_per_token_batches": 1.1e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 8.8e-06, + "output_cost_per_token_batches": 4.4e-06, + "output_cost_per_token_priority": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1-mini": { + "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, + "input_cost_per_token": 4.4e-07, + "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.76e-06, + "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.1e-07, + "input_cost_per_token_batches": 5.5e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-4o-2024-05-13": { + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "output_cost_per_token_batches": 8.25e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5": { + "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, + "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-codex": { + "cache_read_input_token_cost": 1.38e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-mini": { + "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, + "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-nano": { + "cache_read_input_token_cost": 5.5e-09, + "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5-pro": { + "input_cost_per_token": 1.65e-05, + "input_cost_per_token_batches": 8.25e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000132, + "output_cost_per_token_batches": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.1-codex-max": { + "cache_read_input_token_cost": 1.375e-07, + "input_cost_per_token": 1.375e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_batches": 9.625e-07, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_batches": 7.7e-06, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-codex": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.2-pro": { + "input_cost_per_token": 2.31e-05, + "input_cost_per_token_batches": 1.155e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.0001848, + "output_cost_per_token_batches": 9.24e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.3-chat": { + "cache_read_input_token_cost": 1.925e-07, + "input_cost_per_token": 1.925e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.925e-07, + "cache_read_input_token_cost_priority": 3.85e-07, + "input_cost_per_token": 1.925e-06, + "input_cost_per_token_priority": 3.85e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.54e-05, + "output_cost_per_token_priority": 3.08e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-mini": { + "cache_read_input_token_cost": 8.25e-08, + "cache_read_input_token_cost_priority": 1.65e-07, + "input_cost_per_token": 8.25e-07, + "input_cost_per_token_batches": 4.125e-07, + "input_cost_per_token_priority": 1.65e-06, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.95e-06, + "output_cost_per_token_batches": 2.475e-06, + "output_cost_per_token_priority": 9.9e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-nano": { + "cache_read_input_token_cost": 2.2e-08, + "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 1.375e-06, + "output_cost_per_token_batches": 6.875e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/gpt-5.4-pro": { + "input_cost_per_token": 3.3e-05, + "input_cost_per_token_above_272k_tokens": 6.6e-05, + "input_cost_per_token_batches": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 0.000198, + "output_cost_per_token_above_272k_tokens": 0.000297, + "output_cost_per_token_batches": 9.9e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o1-preview": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/o3-deep-research": { + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 1.1e-05, + "litellm_provider": "azure", + "mode": "chat", + "output_cost_per_token": 4.4e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-3-large": { + "input_cost_per_token": 1.43e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-3-small": { + "input_cost_per_token": 2.2e-08, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" + }, + "azure/us/text-embedding-ada-002": { + "input_cost_per_token": 1.1e-07, + "litellm_provider": "azure", + "mode": "embedding", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'" } }