From f808f4e885819199b82587faa726a3c40dbc7c55 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Fri, 30 Oct 2026 05:44:45 +0000 Subject: [PATCH] fix(pricing): add azure gpt-6 astra long-context flex rates --- litellm/model_prices_and_context_window_backup.json | 12 ++++++++++-- model_prices_and_context_window.json | 12 ++++++++++-- 2 files changed, 20 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 0799a298942..b243659f0c7 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -8699,23 +8699,27 @@ "azure/gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, "deprecation_date": "2028-01-11", "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, + "input_cost_per_token_above_272k_tokens_flex": 1e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8747,23 +8751,27 @@ "azure/gpt-6-astra-2026-09-03": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, "deprecation_date": "2028-01-11", "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, + "input_cost_per_token_above_272k_tokens_flex": 1e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 0799a298942..b243659f0c7 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -8699,23 +8699,27 @@ "azure/gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, "deprecation_date": "2028-01-11", "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, + "input_cost_per_token_above_272k_tokens_flex": 1e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8747,23 +8751,27 @@ "azure/gpt-6-astra-2026-09-03": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, "cache_read_input_token_cost": 1e-06, "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, "deprecation_date": "2028-01-11", "input_cost_per_token": 1e-05, "input_cost_per_token_above_272k_tokens": 2e-05, + "input_cost_per_token_above_272k_tokens_flex": 1e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, "output_cost_per_token_above_272k_tokens": 7.5e-05, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-05, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses"