diff --git a/docs/my-website/docs/proxy_server.md b/docs/my-website/docs/proxy_server.md
new file mode 100644
index 000000000..2d5c801b4
--- /dev/null
+++ b/docs/my-website/docs/proxy_server.md
@@ -0,0 +1,34 @@
+# OpenAI Proxy Server
+
+Use this to spin up a proxy api to translate openai api calls to any non-openai model (e.g. Huggingface, TogetherAI, Ollama, etc.)
+
+This works for async + streaming as well. 
+
+## usage
+```python 
+pip install litellm
+```
+
+```python
+litellm --model <your-model-name>
+```
+
+This will host a local proxy api at : **http://localhost:8000**
+
+[**Jump to Code**](https://github.com/BerriAI/litellm/blob/fef4146396d5d87006259e00095a62e3900d6bb4/litellm/proxy.py#L36)
+## test it 
+
+```curl 
+curl --location 'http://0.0.0.0:8000/chat/completions' \
+--header 'Content-Type: application/json' \
+--data '{
+  "model": "gpt-3.5-turbo",
+  "messages": [
+    {
+      "role": "user", 
+      "content": "what do you know?"
+    }
+  ], 
+}'
+```
+
diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js
index 0c8750a47..15a6918bf 100644
--- a/docs/my-website/sidebars.js
+++ b/docs/my-website/sidebars.js
@@ -83,7 +83,7 @@ const sidebars = {
     "exception_mapping",
     'debugging/local_debugging',
     "budget_manager",
-    "proxy_api",
+    "proxy_server",
     {
       type: 'category',
       label: 'Tutorials',
diff --git a/litellm/__pycache__/__init__.cpython-311.pyc b/litellm/__pycache__/__init__.cpython-311.pyc
index 240bff6fb..5a6b2ad79 100644
Binary files a/litellm/__pycache__/__init__.cpython-311.pyc and b/litellm/__pycache__/__init__.cpython-311.pyc differ
diff --git a/litellm/__pycache__/utils.cpython-311.pyc b/litellm/__pycache__/utils.cpython-311.pyc
index e5918250d..2b97701e7 100644
Binary files a/litellm/__pycache__/utils.cpython-311.pyc and b/litellm/__pycache__/utils.cpython-311.pyc differ