From 9f4fbcfe4142de1c5752dd61e7742482331612ad Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 18:51:21 +0000 Subject: [PATCH] chore(prices): sync Azure prices: 14 models [enrichment failed: Google Gemini, 34 held] azure/eu/gpt-5-2025-08-07: input_cost_per_token_batches, input_cost_per_token_priority, output_cost_per_token_batches, output_cost_per_token_priority, cache_read_input_token_cost_priority azure/eu/gpt-5-mini-2025-08-07: input_cost_per_token_batches, input_cost_per_token_priority, output_cost_per_token_batches, output_cost_per_token_priority, cache_read_input_token_cost_priority azure/eu/gpt-5-nano-2025-08-07: input_cost_per_token_batches, output_cost_per_token_batches azure/eu/o1-mini-2024-09-12: azure/eu/o1-preview-2024-09-12: azure/o1-mini-2024-09-12: input_cost_per_token_batches, output_cost_per_token_batches azure/us/gpt-4.1-2025-04-14: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority azure/us/gpt-4.1-mini-2025-04-14: input_cost_per_token_priority, output_cost_per_token_priority, cache_read_input_token_cost_priority azure/us/gpt-4.1-nano-2025-04-14: cache_read_input_token_cost, input_cost_per_token_batches azure/us/gpt-5-2025-08-07: input_cost_per_token_batches, input_cost_per_token_priority, output_cost_per_token_batches, output_cost_per_token_priority, cache_read_input_token_cost_priority azure/us/gpt-5-mini-2025-08-07: input_cost_per_token_batches, input_cost_per_token_priority, output_cost_per_token_batches, output_cost_per_token_priority, cache_read_input_token_cost_priority azure/us/gpt-5-nano-2025-08-07: input_cost_per_token_batches, output_cost_per_token_batches azure/us/o1-mini-2024-09-12: azure/us/o1-preview-2024-09-12: --- ...odel_prices_and_context_window_backup.json | 50 ++++++++++++++++++- model_prices_and_context_window.json | 50 ++++++++++++++++++- 2 files changed, 96 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 1d863977e1e..372ce19e740 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -4296,14 +4296,20 @@ }, "azure/eu/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, "deprecation_date": "2027-02-09", "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", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4329,14 +4335,20 @@ }, "azure/eu/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, "deprecation_date": "2027-02-09", "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4507,12 +4519,15 @@ "cache_read_input_token_cost": 5.5e-09, "deprecation_date": "2027-02-09", "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4566,6 +4581,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4580,6 +4596,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9213,12 +9230,15 @@ "azure/o1-mini-2024-09-12": { "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$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, @@ -9601,8 +9621,10 @@ "azure/us/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", "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", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -9610,6 +9632,8 @@ "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9635,8 +9659,10 @@ "azure/us/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, "input_cost_per_token": 4.4e-07, "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -9644,6 +9670,8 @@ "mode": "chat", "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9668,9 +9696,9 @@ }, "azure/us/gpt-4.1-nano-2025-04-14": { "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, - "input_cost_per_token_batches": 6e-08, + "input_cost_per_token_batches": 5.5e-08, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -9678,6 +9706,7 @@ "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9825,14 +9854,20 @@ }, "azure/us/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, "deprecation_date": "2027-02-09", "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9858,14 +9893,20 @@ }, "azure/us/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, "deprecation_date": "2027-02-09", "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", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9893,12 +9934,15 @@ "cache_read_input_token_cost": 5.5e-09, "deprecation_date": "2027-02-09", "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -10095,6 +10139,7 @@ "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -10109,6 +10154,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 1d863977e1e..372ce19e740 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -4296,14 +4296,20 @@ }, "azure/eu/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, "deprecation_date": "2027-02-09", "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", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4329,14 +4335,20 @@ }, "azure/eu/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, "deprecation_date": "2027-02-09", "input_cost_per_token": 2.75e-07, + "input_cost_per_token_batches": 1.375e-07, + "input_cost_per_token_priority": 4.95e-07, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, + "output_cost_per_token_batches": 1.1e-06, + "output_cost_per_token_priority": 3.96e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4507,12 +4519,15 @@ "cache_read_input_token_cost": 5.5e-09, "deprecation_date": "2027-02-09", "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -4566,6 +4581,7 @@ "mode": "chat", "output_cost_per_token": 4.84e-06, "output_cost_per_token_batches": 2.42e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -4580,6 +4596,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -9213,12 +9230,15 @@ "azure/o1-mini-2024-09-12": { "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 1.1e-06, + "input_cost_per_token_batches": 5.5e-07, "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 4.4e-06, + "output_cost_per_token_batches": 2.2e-06, + "source": "https://prices.azure.com/api/retail/prices?$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, @@ -9601,8 +9621,10 @@ "azure/us/gpt-4.1-2025-04-14": { "deprecation_date": "2027-04-14", "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", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -9610,6 +9632,8 @@ "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9635,8 +9659,10 @@ "azure/us/gpt-4.1-mini-2025-04-14": { "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.1e-07, + "cache_read_input_token_cost_priority": 1.93e-07, "input_cost_per_token": 4.4e-07, "input_cost_per_token_batches": 2.2e-07, + "input_cost_per_token_priority": 7.7e-07, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -9644,6 +9670,8 @@ "mode": "chat", "output_cost_per_token": 1.76e-06, "output_cost_per_token_batches": 8.8e-07, + "output_cost_per_token_priority": 3.08e-06, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9668,9 +9696,9 @@ }, "azure/us/gpt-4.1-nano-2025-04-14": { "deprecation_date": "2027-04-14", - "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, - "input_cost_per_token_batches": 6e-08, + "input_cost_per_token_batches": 5.5e-08, "litellm_provider": "azure", "max_input_tokens": 1047576, "max_output_tokens": 32768, @@ -9678,6 +9706,7 @@ "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9825,14 +9854,20 @@ }, "azure/us/gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.375e-07, + "cache_read_input_token_cost_priority": 2.75e-07, "deprecation_date": "2027-02-09", "input_cost_per_token": 1.375e-06, + "input_cost_per_token_batches": 6.875e-07, + "input_cost_per_token_priority": 2.75e-06, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.1e-05, + "output_cost_per_token_batches": 5.5e-06, + "output_cost_per_token_priority": 2.2e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9858,14 +9893,20 @@ }, "azure/us/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, + "cache_read_input_token_cost_priority": 4.95e-08, "deprecation_date": "2027-02-09", "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", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -9893,12 +9934,15 @@ "cache_read_input_token_cost": 5.5e-09, "deprecation_date": "2027-02-09", "input_cost_per_token": 5.5e-08, + "input_cost_per_token_batches": 2.75e-08, "litellm_provider": "azure", "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.4e-07, + "output_cost_per_token_batches": 2.2e-07, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -10095,6 +10139,7 @@ "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?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true, @@ -10109,6 +10154,7 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 6.6e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus2'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_prompt_caching": true,