From 07cf9dc46f5a4fd3b506f89cc77744f723eff190 Mon Sep 17 00:00:00 2001 From: Yujong Lee Date: Wed, 2 Sep 2026 08:10:52 -0700 Subject: [PATCH 1/2] feat(models): add Azure DeepSeek V4 Flash 0731 --- .../model_prices_and_context_window_backup.json | 16 ++++++++++++++++ model_prices_and_context_window.json | 16 ++++++++++++++++ 2 files changed, 32 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index a3cfb300ea6..893ac49f5c7 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -10171,6 +10171,22 @@ "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/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 2.8e-08, "deprecation_date": "2026-12-03", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index a3cfb300ea6..893ac49f5c7 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -10171,6 +10171,22 @@ "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/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 2.8e-08, "deprecation_date": "2026-12-03", From a9d3a0746c582de8910d0a7078489ac961e436e8 Mon Sep 17 00:00:00 2001 From: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Date: Wed, 2 Sep 2026 10:59:11 -0700 Subject: [PATCH 2/2] fix(models): price Azure DeepSeek V4 Flash 0731 from its own meters under the catalog id --- ...odel_prices_and_context_window_backup.json | 22 +++---------------- model_prices_and_context_window.json | 22 +++---------------- 2 files changed, 6 insertions(+), 38 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 893ac49f5c7..0af5a89742e 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -10172,31 +10172,15 @@ "supports_tool_choice": true }, "azure_ai/DeepSeek-V4-Flash-0731": { - "cache_read_input_token_cost": 2.8e-08, + "cache_read_input_token_cost": 1.4e-08, "deprecation_date": "2026-12-03", - "input_cost_per_token": 1.9e-07, + "input_cost_per_token": 4.4e-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/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, + "output_cost_per_token": 1.32e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", "supports_function_calling": true, "supports_prompt_caching": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 893ac49f5c7..0af5a89742e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -10172,31 +10172,15 @@ "supports_tool_choice": true }, "azure_ai/DeepSeek-V4-Flash-0731": { - "cache_read_input_token_cost": 2.8e-08, + "cache_read_input_token_cost": 1.4e-08, "deprecation_date": "2026-12-03", - "input_cost_per_token": 1.9e-07, + "input_cost_per_token": 4.4e-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/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, + "output_cost_per_token": 1.32e-06, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", "supports_function_calling": true, "supports_prompt_caching": true,