From b1b6747869fecabe038733b4bf9c55972dcbac4e Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Thu, 17 Sep 2026 13:31:57 +0000 Subject: [PATCH 1/4] fix(models): Azure retirement dates and Bedrock Mantle Grok 4.3 context window Azure schedule: https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule AWS card: https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-xai-grok-4-3.html Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 60 +++++++++++++++++-- model_prices_and_context_window.json | 60 +++++++++++++++++-- 2 files changed, 108 insertions(+), 12 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index c565b6ecc4b..7aae4e8bf53 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -5282,7 +5282,7 @@ "supports_web_search": false }, "azure/gpt-4.1-nano": { - "deprecation_date": "2027-04-14", + "deprecation_date": "2026-10-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, @@ -5316,7 +5316,7 @@ "supports_vision": true }, "azure/gpt-4.1-nano-2025-04-14": { - "deprecation_date": "2027-04-14", + "deprecation_date": "2026-10-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, @@ -9473,7 +9473,7 @@ ] }, "azure/gpt-image-1.5": { - "deprecation_date": "2027-06-16", + "deprecation_date": "2026-12-16", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, @@ -9487,7 +9487,7 @@ }, "azure/gpt-image-1.5-2025-12-16": { "cache_read_input_token_cost": 1.25e-06, - "deprecation_date": "2027-06-16", + "deprecation_date": "2026-12-16", "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", @@ -10189,7 +10189,7 @@ "supports_web_search": false }, "azure/us/gpt-4.1-nano-2025-04-14": { - "deprecation_date": "2027-04-14", + "deprecation_date": "2026-10-14", "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 5.5e-08, @@ -57927,7 +57927,7 @@ "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2e-07, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 131072, + "max_input_tokens": 1048576, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -67450,6 +67450,7 @@ "source": "https://api.together.ai/v1/models" }, "azure/eu/codex-mini": { + "deprecation_date": "2026-11-15", "cache_read_input_token_cost": 4.13e-07, "input_cost_per_token": 1.65e-06, "litellm_provider": "azure", @@ -67465,6 +67466,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1": { + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_priority": 9.63e-07, "input_cost_per_token": 2.2e-06, @@ -67478,6 +67480,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-mini": { + "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, @@ -67491,6 +67494,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-nano": { + "deprecation_date": "2026-10-14", "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 5.5e-08, @@ -67501,6 +67505,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4o-2024-05-13": { + "deprecation_date": "2026-10-01", "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", @@ -67510,6 +67515,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_priority": 2.75e-07, "input_cost_per_token": 1.375e-06, @@ -67523,6 +67529,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-codex": { + "deprecation_date": "2027-03-17", "cache_read_input_token_cost": 1.38e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", @@ -67531,6 +67538,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-mini": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 2.75e-08, "cache_read_input_token_cost_priority": 4.95e-08, "input_cost_per_token": 2.75e-07, @@ -67544,6 +67552,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-nano": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 5.5e-09, "input_cost_per_token": 5.5e-08, "input_cost_per_token_batches": 2.75e-08, @@ -67554,6 +67563,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-pro": { + "deprecation_date": "2027-04-07", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", @@ -67563,6 +67573,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex-max": { + "deprecation_date": "2027-05-18", "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", @@ -67571,6 +67582,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2": { + "deprecation_date": "2027-06-08", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 1.925e-06, @@ -67584,6 +67596,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-chat": { + "deprecation_date": "2026-06-29", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", @@ -67592,6 +67605,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-codex": { + "deprecation_date": "2027-07-13", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", @@ -67609,6 +67623,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.3-chat": { + "deprecation_date": "2026-06-29", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", @@ -67617,6 +67632,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.3-codex": { + "deprecation_date": "2027-08-24", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 1.925e-06, @@ -67628,6 +67644,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-mini": { + "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 8.25e-08, "cache_read_input_token_cost_priority": 1.65e-07, "input_cost_per_token": 8.25e-07, @@ -67641,6 +67658,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-nano": { + "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 2.2e-08, "input_cost_per_token": 2.2e-07, "input_cost_per_token_batches": 1.1e-07, @@ -67651,6 +67669,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-pro": { + "deprecation_date": "2027-09-07", "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, @@ -67693,6 +67712,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-2025-04-16": { + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, @@ -67703,6 +67723,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-deep-research": { + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 2.75e-06, "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", @@ -67711,6 +67732,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o4-mini-2025-04-16": { + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 3.03e-07, "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, @@ -67721,18 +67743,21 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-3-large": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-3-small": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-ada-002": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "mode": "embedding", @@ -67779,6 +67804,7 @@ "supports_web_search": true }, "azure/us/codex-mini": { + "deprecation_date": "2026-11-15", "cache_read_input_token_cost": 4.13e-07, "input_cost_per_token": 1.65e-06, "litellm_provider": "azure", @@ -67794,6 +67820,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1": { + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_priority": 9.63e-07, "input_cost_per_token": 2.2e-06, @@ -67807,6 +67834,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-mini": { + "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, @@ -67820,6 +67848,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-nano": { + "deprecation_date": "2026-10-14", "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 5.5e-08, @@ -67830,6 +67859,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4o-2024-05-13": { + "deprecation_date": "2026-10-01", "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", @@ -67839,6 +67869,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_priority": 2.75e-07, "input_cost_per_token": 1.375e-06, @@ -67852,6 +67883,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-codex": { + "deprecation_date": "2027-03-17", "cache_read_input_token_cost": 1.38e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", @@ -67860,6 +67892,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-mini": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 2.75e-08, "cache_read_input_token_cost_priority": 4.95e-08, "input_cost_per_token": 2.75e-07, @@ -67873,6 +67906,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-nano": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 5.5e-09, "input_cost_per_token": 5.5e-08, "input_cost_per_token_batches": 2.75e-08, @@ -67883,6 +67917,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-pro": { + "deprecation_date": "2027-04-07", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", @@ -67892,6 +67927,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex-max": { + "deprecation_date": "2027-05-18", "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", @@ -67900,6 +67936,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2": { + "deprecation_date": "2027-06-08", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 1.925e-06, @@ -67913,6 +67950,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-chat": { + "deprecation_date": "2026-06-29", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", @@ -67921,6 +67959,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-codex": { + "deprecation_date": "2027-07-13", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", @@ -67938,6 +67977,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.3-chat": { + "deprecation_date": "2026-06-29", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", @@ -67946,6 +67986,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.3-codex": { + "deprecation_date": "2027-08-24", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 1.925e-06, @@ -67957,6 +67998,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-mini": { + "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 8.25e-08, "cache_read_input_token_cost_priority": 1.65e-07, "input_cost_per_token": 8.25e-07, @@ -67970,6 +68012,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-nano": { + "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 2.2e-08, "input_cost_per_token": 2.2e-07, "input_cost_per_token_batches": 1.1e-07, @@ -67980,6 +68023,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-pro": { + "deprecation_date": "2027-09-07", "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, @@ -68009,6 +68053,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/o3-deep-research": { + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 2.75e-06, "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", @@ -68017,18 +68062,21 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-3-large": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-3-small": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-ada-002": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "mode": "embedding", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index c565b6ecc4b..7aae4e8bf53 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -5282,7 +5282,7 @@ "supports_web_search": false }, "azure/gpt-4.1-nano": { - "deprecation_date": "2027-04-14", + "deprecation_date": "2026-10-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, @@ -5316,7 +5316,7 @@ "supports_vision": true }, "azure/gpt-4.1-nano-2025-04-14": { - "deprecation_date": "2027-04-14", + "deprecation_date": "2026-10-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, @@ -9473,7 +9473,7 @@ ] }, "azure/gpt-image-1.5": { - "deprecation_date": "2027-06-16", + "deprecation_date": "2026-12-16", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, @@ -9487,7 +9487,7 @@ }, "azure/gpt-image-1.5-2025-12-16": { "cache_read_input_token_cost": 1.25e-06, - "deprecation_date": "2027-06-16", + "deprecation_date": "2026-12-16", "input_cost_per_token": 5e-06, "input_cost_per_image_token": 8e-06, "litellm_provider": "azure", @@ -10189,7 +10189,7 @@ "supports_web_search": false }, "azure/us/gpt-4.1-nano-2025-04-14": { - "deprecation_date": "2027-04-14", + "deprecation_date": "2026-10-14", "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 5.5e-08, @@ -57927,7 +57927,7 @@ "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 2e-07, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 131072, + "max_input_tokens": 1048576, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -67450,6 +67450,7 @@ "source": "https://api.together.ai/v1/models" }, "azure/eu/codex-mini": { + "deprecation_date": "2026-11-15", "cache_read_input_token_cost": 4.13e-07, "input_cost_per_token": 1.65e-06, "litellm_provider": "azure", @@ -67465,6 +67466,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1": { + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_priority": 9.63e-07, "input_cost_per_token": 2.2e-06, @@ -67478,6 +67480,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-mini": { + "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, @@ -67491,6 +67494,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4.1-nano": { + "deprecation_date": "2026-10-14", "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 5.5e-08, @@ -67501,6 +67505,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-4o-2024-05-13": { + "deprecation_date": "2026-10-01", "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", @@ -67510,6 +67515,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_priority": 2.75e-07, "input_cost_per_token": 1.375e-06, @@ -67523,6 +67529,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-codex": { + "deprecation_date": "2027-03-17", "cache_read_input_token_cost": 1.38e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", @@ -67531,6 +67538,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-mini": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 2.75e-08, "cache_read_input_token_cost_priority": 4.95e-08, "input_cost_per_token": 2.75e-07, @@ -67544,6 +67552,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-nano": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 5.5e-09, "input_cost_per_token": 5.5e-08, "input_cost_per_token_batches": 2.75e-08, @@ -67554,6 +67563,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5-pro": { + "deprecation_date": "2027-04-07", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", @@ -67563,6 +67573,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.1-codex-max": { + "deprecation_date": "2027-05-18", "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", @@ -67571,6 +67582,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2": { + "deprecation_date": "2027-06-08", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 1.925e-06, @@ -67584,6 +67596,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-chat": { + "deprecation_date": "2026-06-29", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", @@ -67592,6 +67605,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.2-codex": { + "deprecation_date": "2027-07-13", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", @@ -67609,6 +67623,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.3-chat": { + "deprecation_date": "2026-06-29", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", @@ -67617,6 +67632,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.3-codex": { + "deprecation_date": "2027-08-24", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 1.925e-06, @@ -67628,6 +67644,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-mini": { + "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 8.25e-08, "cache_read_input_token_cost_priority": 1.65e-07, "input_cost_per_token": 8.25e-07, @@ -67641,6 +67658,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-nano": { + "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 2.2e-08, "input_cost_per_token": 2.2e-07, "input_cost_per_token_batches": 1.1e-07, @@ -67651,6 +67669,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.4-pro": { + "deprecation_date": "2027-09-07", "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, @@ -67693,6 +67712,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-2025-04-16": { + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 5.5e-07, "input_cost_per_token": 2.2e-06, "input_cost_per_token_batches": 1.1e-06, @@ -67703,6 +67723,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o3-deep-research": { + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 2.75e-06, "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", @@ -67711,6 +67732,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/o4-mini-2025-04-16": { + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 3.03e-07, "input_cost_per_token": 1.21e-06, "input_cost_per_token_batches": 6.05e-07, @@ -67721,18 +67743,21 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-3-large": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-3-small": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/text-embedding-ada-002": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "mode": "embedding", @@ -67779,6 +67804,7 @@ "supports_web_search": true }, "azure/us/codex-mini": { + "deprecation_date": "2026-11-15", "cache_read_input_token_cost": 4.13e-07, "input_cost_per_token": 1.65e-06, "litellm_provider": "azure", @@ -67794,6 +67820,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1": { + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_priority": 9.63e-07, "input_cost_per_token": 2.2e-06, @@ -67807,6 +67834,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-mini": { + "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, @@ -67820,6 +67848,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4.1-nano": { + "deprecation_date": "2026-10-14", "cache_read_input_token_cost": 2.8e-08, "input_cost_per_token": 1.1e-07, "input_cost_per_token_batches": 5.5e-08, @@ -67830,6 +67859,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-4o-2024-05-13": { + "deprecation_date": "2026-10-01", "input_cost_per_token": 5.5e-06, "input_cost_per_token_batches": 2.75e-06, "litellm_provider": "azure", @@ -67839,6 +67869,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 1.375e-07, "cache_read_input_token_cost_priority": 2.75e-07, "input_cost_per_token": 1.375e-06, @@ -67852,6 +67883,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-codex": { + "deprecation_date": "2027-03-17", "cache_read_input_token_cost": 1.38e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", @@ -67860,6 +67892,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-mini": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 2.75e-08, "cache_read_input_token_cost_priority": 4.95e-08, "input_cost_per_token": 2.75e-07, @@ -67873,6 +67906,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-nano": { + "deprecation_date": "2027-02-09", "cache_read_input_token_cost": 5.5e-09, "input_cost_per_token": 5.5e-08, "input_cost_per_token_batches": 2.75e-08, @@ -67883,6 +67917,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5-pro": { + "deprecation_date": "2027-04-07", "input_cost_per_token": 1.65e-05, "input_cost_per_token_batches": 8.25e-06, "litellm_provider": "azure", @@ -67892,6 +67927,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.1-codex-max": { + "deprecation_date": "2027-05-18", "cache_read_input_token_cost": 1.375e-07, "input_cost_per_token": 1.375e-06, "litellm_provider": "azure", @@ -67900,6 +67936,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2": { + "deprecation_date": "2027-06-08", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 1.925e-06, @@ -67913,6 +67950,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-chat": { + "deprecation_date": "2026-06-29", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", @@ -67921,6 +67959,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.2-codex": { + "deprecation_date": "2027-07-13", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", @@ -67938,6 +67977,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.3-chat": { + "deprecation_date": "2026-06-29", "cache_read_input_token_cost": 1.925e-07, "input_cost_per_token": 1.925e-06, "litellm_provider": "azure", @@ -67946,6 +67986,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.3-codex": { + "deprecation_date": "2027-08-24", "cache_read_input_token_cost": 1.925e-07, "cache_read_input_token_cost_priority": 3.85e-07, "input_cost_per_token": 1.925e-06, @@ -67957,6 +67998,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-mini": { + "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 8.25e-08, "cache_read_input_token_cost_priority": 1.65e-07, "input_cost_per_token": 8.25e-07, @@ -67970,6 +68012,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-nano": { + "deprecation_date": "2027-09-21", "cache_read_input_token_cost": 2.2e-08, "input_cost_per_token": 2.2e-07, "input_cost_per_token_batches": 1.1e-07, @@ -67980,6 +68023,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.4-pro": { + "deprecation_date": "2027-09-07", "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, @@ -68009,6 +68053,7 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/o3-deep-research": { + "deprecation_date": "2026-11-19", "cache_read_input_token_cost": 2.75e-06, "input_cost_per_token": 1.1e-05, "litellm_provider": "azure", @@ -68017,18 +68062,21 @@ "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-3-large": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 1.43e-07, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-3-small": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 2.2e-08, "litellm_provider": "azure", "mode": "embedding", "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/text-embedding-ada-002": { + "deprecation_date": "2028-02-09", "input_cost_per_token": 1.1e-07, "litellm_provider": "azure", "mode": "embedding", From f79c3ebfee7982063dafef268daf81c03dce9bc8 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Thu, 17 Sep 2026 13:48:59 +0000 Subject: [PATCH 2/4] fix(models): align Bedrock Mantle Grok 4.3 GovCloud context window with model card Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 2 +- model_prices_and_context_window.json | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 7aae4e8bf53..a39017f0ab9 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -63653,7 +63653,7 @@ "bedrock_mantle/us-gov-west-1/xai.grok-4.3": { "use_openai_responses_path": true, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 131072, + "max_input_tokens": 1048576, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 7aae4e8bf53..a39017f0ab9 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -63653,7 +63653,7 @@ "bedrock_mantle/us-gov-west-1/xai.grok-4.3": { "use_openai_responses_path": true, "litellm_provider": "bedrock_mantle", - "max_input_tokens": 131072, + "max_input_tokens": 1048576, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", From 14e4b9f906c5ca3ef6f256ed622688ee55076c0c Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Thu, 17 Sep 2026 19:14:04 +0000 Subject: [PATCH 3/4] fix(gemini): gemini-3.5-flash-lite priority cache read is $0.054/M Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 2 +- model_prices_and_context_window.json | 2 +- .../llm_cost_calc/test_llm_cost_calc_utils.py | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index a39017f0ab9..5fd860a040c 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -27838,7 +27838,7 @@ "gemini/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_flex": 2e-08, - "cache_read_input_token_cost_priority": 5e-08, + "cache_read_input_token_cost_priority": 5.4e-08, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index a39017f0ab9..5fd860a040c 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -27838,7 +27838,7 @@ "gemini/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_flex": 2e-08, - "cache_read_input_token_cost_priority": 5e-08, + "cache_read_input_token_cost_priority": 5.4e-08, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index 798d657cce7..a285d5431b7 100644 --- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -3426,7 +3426,7 @@ GEMINI_36_FLASH_SERVICE_TIER_PRICING = [ GEMINI_35_FLASH_LITE_TIER_RATES_BY_SURFACE = [ ("gemini", None, 3e-07, 2.5e-06, 3e-08), ("gemini", "flex", 1.5e-07, 1.25e-06, 2e-08), - ("gemini", "priority", 5.4e-07, 4.5e-06, 5e-08), + ("gemini", "priority", 5.4e-07, 4.5e-06, 5.4e-08), ("vertex_ai", None, 3e-07, 2.5e-06, 3e-08), ("vertex_ai", "flex", 1.5e-07, 1.25e-06, 1.5e-08), ("vertex_ai", "priority", 5.4e-07, 4.5e-06, 5.4e-08), From 86f625736c2215c2f292cf69a709e66d45516add Mon Sep 17 00:00:00 2001 From: kerry Date: Fri, 18 Sep 2026 01:13:41 +0000 Subject: [PATCH 4/4] Revert "fix(gemini): gemini-3.5-flash-lite priority cache read is $0.054/M" This reverts commit 14e4b9f906c5ca3ef6f256ed622688ee55076c0c. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 2 +- model_prices_and_context_window.json | 2 +- .../llm_cost_calc/test_llm_cost_calc_utils.py | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 5fd860a040c..a39017f0ab9 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -27838,7 +27838,7 @@ "gemini/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_flex": 2e-08, - "cache_read_input_token_cost_priority": 5.4e-08, + "cache_read_input_token_cost_priority": 5e-08, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 5fd860a040c..a39017f0ab9 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -27838,7 +27838,7 @@ "gemini/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_flex": 2e-08, - "cache_read_input_token_cost_priority": 5.4e-08, + "cache_read_input_token_cost_priority": 5e-08, "input_cost_per_token": 3e-07, "input_cost_per_token_batches": 1.5e-07, "input_cost_per_token_flex": 1.5e-07, diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index a285d5431b7..798d657cce7 100644 --- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -3426,7 +3426,7 @@ GEMINI_36_FLASH_SERVICE_TIER_PRICING = [ GEMINI_35_FLASH_LITE_TIER_RATES_BY_SURFACE = [ ("gemini", None, 3e-07, 2.5e-06, 3e-08), ("gemini", "flex", 1.5e-07, 1.25e-06, 2e-08), - ("gemini", "priority", 5.4e-07, 4.5e-06, 5.4e-08), + ("gemini", "priority", 5.4e-07, 4.5e-06, 5e-08), ("vertex_ai", None, 3e-07, 2.5e-06, 3e-08), ("vertex_ai", "flex", 1.5e-07, 1.25e-06, 1.5e-08), ("vertex_ai", "priority", 5.4e-07, 4.5e-06, 5.4e-08),