docs

docs/my-website/docs/tutorials/mock_completion.md

@@ -0,0 +1,15 @@
+# Mock Completion Responses - Save Testing Costs
+
+Trying to test making LLM Completion calls without calling the LLM APIs ? 
+Pass `mock_response` to `litellm.completion` and litellm will directly return the response without neededing the call the LLM API and spend $$ 
+
+## Using `mock_response`
+
+```python
+from litellm import completion 
+
+model = "gpt-3.5-turbo"
+messages = [{"role":"user", "content":"Why is LiteLLM amazing?"}]
+
+completion(model=model, messages=messages, mock_response="It's simple to use and easy to get started")
+```

docs/my-website/sidebars.js

@@ -88,6 +88,7 @@ const sidebars = {
         'tutorials/ab_test_llms',
         'tutorials/huggingface_tutorial', 
         'tutorials/TogetherAI_liteLLM', 
+        'tutorials/mock_completion',
         'tutorials/finetuned_chat_gpt',
         'tutorials/sagemaker_llms',
         'tutorials/text_completion',