diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 04db405dd3c..be90ee32687 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -1587,13 +1587,23 @@ "max_tokens": 8192, "max_input_tokens": 128000, "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "input_cost_per_token_cache_hit": 0.0, - "output_cost_per_token": 0.0, + "input_cost_per_token": 0.00000135, + "output_cost_per_token": 0.0000054, "litellm_provider": "azure_ai", "mode": "chat", - "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367" + }, + "azure_ai/deepseek-v3": { + "max_tokens": 8192, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "input_cost_per_token": 0.00000114, + "output_cost_per_token": 0.00000456, + "litellm_provider": "azure_ai", + "mode": "chat", + "supports_tool_choice": true, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438" }, "azure_ai/jamba-instruct": { "max_tokens": 4096,