From 2c334264431e75ce1dcc6fb07a48425e8fb2a28a Mon Sep 17 00:00:00 2001 From: Ishaan Jaffer Date: Fri, 30 Jan 2026 13:35:33 -0800 Subject: [PATCH] init: azure_ai/azure-model-router --- litellm/model_prices_and_context_window_backup.json | 8 ++++++++ model_prices_and_context_window.json | 8 ++++++++ 2 files changed, 16 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index d874e6ba578..0f84bba941d 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -1517,6 +1517,14 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "azure_ai/model_router": { + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 0, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-services/", + "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/ where deployment-name is your Azure deployment (e.g., azure-model-router)" + }, "azure/eu/gpt-4o-2024-08-06": { "deprecation_date": "2026-02-27", "cache_read_input_token_cost": 1.375e-06, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index d874e6ba578..0f84bba941d 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -1517,6 +1517,14 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "azure_ai/model_router": { + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 0, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-services/", + "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/ where deployment-name is your Azure deployment (e.g., azure-model-router)" + }, "azure/eu/gpt-4o-2024-08-06": { "deprecation_date": "2026-02-27", "cache_read_input_token_cost": 1.375e-06,