diff --git a/docs/my-website/docs/completion/mock_requests.md b/docs/my-website/docs/completion/mock_requests.md
new file mode 100644
index 0000000000..0e8bc02fb5
--- /dev/null
+++ b/docs/my-website/docs/completion/mock_requests.md
@@ -0,0 +1,39 @@
+# Mock Requests
+
+For testing purposes, you can set `mock_requests=True` while calling the completion endpoint. 
+
+This will return a response object with a default response, without calling the LLM APIs. 
+
+```python
+from litellm import completion 
+
+model = "gpt-3.5-turbo"
+messages = [{"role":"user", "content":"This is a test request"}]
+
+completion(model=model, messages=messages, mock_request=True)
+```
+
+## Mock Response Object 
+
+```
+{
+  "choices": [
+    {
+      "finish_reason": "stop",
+      "index": 0,
+      "message": {
+        "content": "This is a mock request",
+        "role": "assistant",
+        "logprobs": null
+      }
+    }
+  ],
+  "created": 1694459929.4496052,
+  "model": "MockResponse",
+  "usage": {
+    "prompt_tokens": null,
+    "completion_tokens": null,
+    "total_tokens": null
+  }
+}
+```
\ No newline at end of file
diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js
index 12bbff8660..5476f477ed 100644
--- a/docs/my-website/sidebars.js
+++ b/docs/my-website/sidebars.js
@@ -34,7 +34,8 @@ const sidebars = {
         "completion/model_alias", 
         "completion/reliable_completions", 
         "completion/stream", 
-        "completion/batching"
+        "completion/batching",
+        "completion/mock_requests",
       ],
     },
     {