From a402e4ebdac580e0669312ea6526d3a49cc8824b Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Fri, 30 Oct 2026 13:11:17 +0000 Subject: [PATCH] fix(model_prices): absorb Gemini long-prompt batch rates and Azure GPT-6 Astra long-context flex rates Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 36 ++++++++++++++----- model_prices_and_context_window.json | 36 ++++++++++++++----- 2 files changed, 54 insertions(+), 18 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 8dbc5d5647e..1bc4a6caa79 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -8715,7 +8715,7 @@ "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8742,7 +8742,11 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, + "input_cost_per_token_above_272k_tokens_flex": 1e-05, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-05 }, "azure/gpt-6-astra-2026-09-03": { "cache_creation_input_token_cost": 1.25e-05, @@ -8763,7 +8767,7 @@ "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, - "source": "https://prices.azure.com/api/retail/prices?$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" @@ -8790,7 +8794,11 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, + "input_cost_per_token_above_272k_tokens_flex": 1e-05, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-05 }, "azure/gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, @@ -30856,8 +30864,9 @@ "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions", - "tpm": 10000000 + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "tpm": 10000000, + "input_cost_per_token_batches": 7.5e-08 }, "gemini/gemini-embedding-2": { "input_cost_per_audio_token": 6.5e-06, @@ -31713,7 +31722,10 @@ "input_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, - "supports_url_context": true + "supports_url_context": true, + "cache_read_input_token_cost_above_200k_tokens_batches": 2.5e-07, + "input_cost_per_token_above_200k_tokens_batches": 1.25e-06, + "output_cost_per_token_above_200k_tokens_batches": 7.5e-06 }, "gemini/gemini-2.5-computer-use-preview-10-2025": { "deprecation_date": "2026-07-28", @@ -32280,7 +32292,10 @@ "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "output_cost_per_token_flex": 6e-06, + "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens_batches": 9e-06 }, "gemini/gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, @@ -32343,7 +32358,10 @@ "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "output_cost_per_token_flex": 6e-06, + "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens_batches": 9e-06 }, "gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 8dbc5d5647e..1bc4a6caa79 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -8715,7 +8715,7 @@ "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8742,7 +8742,11 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, + "input_cost_per_token_above_272k_tokens_flex": 1e-05, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-05 }, "azure/gpt-6-astra-2026-09-03": { "cache_creation_input_token_cost": 1.25e-05, @@ -8763,7 +8767,7 @@ "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, - "source": "https://prices.azure.com/api/retail/prices?$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" @@ -8790,7 +8794,11 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-05, + "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06, + "input_cost_per_token_above_272k_tokens_flex": 1e-05, + "output_cost_per_token_above_272k_tokens_flex": 3.75e-05 }, "azure/gpt-6-luna": { "cache_creation_input_token_cost": 1.25e-07, @@ -30856,8 +30864,9 @@ "output_cost_per_token": 0, "output_vector_size": 3072, "rpm": 10000, - "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions", - "tpm": 10000000 + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "tpm": 10000000, + "input_cost_per_token_batches": 7.5e-08 }, "gemini/gemini-embedding-2": { "input_cost_per_audio_token": 6.5e-06, @@ -31713,7 +31722,10 @@ "input_cost_per_token_flex": 6.25e-07, "output_cost_per_token_batches": 5e-06, "output_cost_per_token_flex": 5e-06, - "supports_url_context": true + "supports_url_context": true, + "cache_read_input_token_cost_above_200k_tokens_batches": 2.5e-07, + "input_cost_per_token_above_200k_tokens_batches": 1.25e-06, + "output_cost_per_token_above_200k_tokens_batches": 7.5e-06 }, "gemini/gemini-2.5-computer-use-preview-10-2025": { "deprecation_date": "2026-07-28", @@ -32280,7 +32292,10 @@ "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "output_cost_per_token_flex": 6e-06, + "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens_batches": 9e-06 }, "gemini/gemini-3.1-pro-preview-customtools": { "prompt_cache_min_tokens": 4096, @@ -32343,7 +32358,10 @@ "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 1e-06, - "output_cost_per_token_flex": 6e-06 + "output_cost_per_token_flex": 6e-06, + "cache_read_input_token_cost_above_200k_tokens_batches": 4e-07, + "input_cost_per_token_above_200k_tokens_batches": 2e-06, + "output_cost_per_token_above_200k_tokens_batches": 9e-06 }, "gemini-3-flash-preview": { "cache_read_input_audio_token_cost": 1e-07,