diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 6d814c731d..0005269ad5 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -7813,14 +7813,14 @@ "supports_vision": true }, "deepseek-chat": { - "cache_read_input_token_cost": 6e-08, - "input_cost_per_token": 6e-07, + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 2.8e-07, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.7e-06, + "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" @@ -7834,14 +7834,14 @@ "supports_tool_choice": true }, "deepseek-reasoner": { - "cache_read_input_token_cost": 6e-08, - "input_cost_per_token": 6e-07, + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 2.8e-07, "litellm_provider": "deepseek", "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.7e-06, + "output_cost_per_token": 4.2e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" @@ -10045,15 +10045,15 @@ }, "deepseek/deepseek-chat": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 7e-08, - "input_cost_per_token": 2.7e-07, - "input_cost_per_token_cache_hit": 7e-08, + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 2.8e-07, + "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", - "max_input_tokens": 65536, + "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 1.1e-06, + "output_cost_per_token": 4.2e-07, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, @@ -10089,14 +10089,15 @@ "supports_tool_choice": true }, "deepseek/deepseek-reasoner": { - "input_cost_per_token": 5.5e-07, - "input_cost_per_token_cache_hit": 1.4e-07, + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 2.8e-07, + "input_cost_per_token_cache_hit": 2.8e-08, "litellm_provider": "deepseek", - "max_input_tokens": 65536, + "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 2.19e-06, + "output_cost_per_token": 4.2e-07, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true,