diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 43f7bde5da..87f3566ae8 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -18826,13 +18826,14 @@ "supports_tool_choice": true }, "groq/openai/gpt-oss-120b": { + "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 32766, "max_tokens": 32766, "mode": "chat", - "output_cost_per_token": 7.5e-07, + "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -18841,13 +18842,14 @@ "supports_web_search": true }, "groq/openai/gpt-oss-20b": { - "input_cost_per_token": 1e-07, + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_token": 7.5e-08, "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 5e-07, + "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 43f7bde5da..87f3566ae8 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -18826,13 +18826,14 @@ "supports_tool_choice": true }, "groq/openai/gpt-oss-120b": { + "cache_read_input_token_cost": 7.5e-08, "input_cost_per_token": 1.5e-07, "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 32766, "max_tokens": 32766, "mode": "chat", - "output_cost_per_token": 7.5e-07, + "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true, @@ -18841,13 +18842,14 @@ "supports_web_search": true }, "groq/openai/gpt-oss-20b": { - "input_cost_per_token": 1e-07, + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_token": 7.5e-08, "litellm_provider": "groq", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 5e-07, + "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_reasoning": true,