From be5997f3664f7359204fe58f3111a93f24471aee Mon Sep 17 00:00:00 2001 From: Yujong Lee Date: Mon, 31 Aug 2026 14:48:16 -0700 Subject: [PATCH 1/2] feat: add Azure AI DeepSeek V4 Flash 0731 pricing --- model_prices_and_context_window.json | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 7071eaa0807..6b4a9818554 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -9959,6 +9959,22 @@ "supports_reasoning": true, "supports_tool_choice": true }, + "azure_ai/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-12-03", + "input_cost_per_token": 1.9e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.1e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "azure_ai/embed-v-4-0": { "input_cost_per_token": 1.2e-07, "litellm_provider": "azure_ai", From 1a80b7ae252e017b937dfb9cf665cc04152ce4ec Mon Sep 17 00:00:00 2001 From: Yujong Lee Date: Mon, 31 Aug 2026 15:00:39 -0700 Subject: [PATCH 2/2] fix: sync Azure AI model backup registry --- .../model_prices_and_context_window_backup.json | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 7071eaa0807..6b4a9818554 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -9959,6 +9959,22 @@ "supports_reasoning": true, "supports_tool_choice": true }, + "azure_ai/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 2.8e-08, + "deprecation_date": "2026-12-03", + "input_cost_per_token": 1.9e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5.1e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "azure_ai/embed-v-4-0": { "input_cost_per_token": 1.2e-07, "litellm_provider": "azure_ai",