diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index a60743c65..daf2c502a 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -1273,6 +1273,26 @@ "mode": "chat", "supports_function_calling": true }, + "cerebras/llama3.1-8b": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.0000001, + "output_cost_per_token": 0.0000001, + "litellm_provider": "cerebras", + "mode": "chat", + "supports_function_calling": true + }, + "cerebras/llama3.1-70b": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.0000006, + "output_cost_per_token": 0.0000006, + "litellm_provider": "cerebras", + "mode": "chat", + "supports_function_calling": true + }, "friendliai/mixtral-8x7b-instruct-v0-1": { "max_tokens": 32768, "max_input_tokens": 32768, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index a60743c65..daf2c502a 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -1273,6 +1273,26 @@ "mode": "chat", "supports_function_calling": true }, + "cerebras/llama3.1-8b": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.0000001, + "output_cost_per_token": 0.0000001, + "litellm_provider": "cerebras", + "mode": "chat", + "supports_function_calling": true + }, + "cerebras/llama3.1-70b": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.0000006, + "output_cost_per_token": 0.0000006, + "litellm_provider": "cerebras", + "mode": "chat", + "supports_function_calling": true + }, "friendliai/mixtral-8x7b-instruct-v0-1": { "max_tokens": 32768, "max_input_tokens": 32768,