diff --git a/docs/my-website/docs/completion/stream.md b/docs/my-website/docs/completion/stream.md
index da578f7dee8..6cb813ae934 100644
--- a/docs/my-website/docs/completion/stream.md
+++ b/docs/my-website/docs/completion/stream.md
@@ -34,9 +34,11 @@ print(response)
 
 ## Async Streaming
 We've implemented an `__anext__()` function in the streaming object returned. This enables async iteration over the streaming object. 
+
 ### Usage
+Here's an example of using it with openai. But this 
 ```
-from litellm import acompletion
+from litellm import completion
 import asyncio
 
 def logger_fn(model_call_object: dict):
@@ -46,11 +48,10 @@ def logger_fn(model_call_object: dict):
 user_message = "Hello, how are you?"
 messages = [{"content": user_message, "role": "user"}]
 
-# # test on ai21 completion call
-async def ai21_async_completion_call():
+async def completion_call():
     try:
         response = completion(
-            model="j2-ultra", messages=messages, stream=True, logger_fn=logger_fn
+            model="gpt-3.5-turbo", messages=messages, stream=True, logger_fn=logger_fn
         )
         print(f"response: {response}")
         complete_response = ""
@@ -67,5 +68,5 @@ async def ai21_async_completion_call():
         print(f"error occurred: {traceback.format_exc()}")
         pass
 
-asyncio.run(ai21_async_completion_call())
+asyncio.run(completion_call())
 ```
\ No newline at end of file
diff --git a/litellm/__pycache__/__init__.cpython-311.pyc b/litellm/__pycache__/__init__.cpython-311.pyc
index a95ce65c852..6c515ddae08 100644
Binary files a/litellm/__pycache__/__init__.cpython-311.pyc and b/litellm/__pycache__/__init__.cpython-311.pyc differ
diff --git a/litellm/__pycache__/main.cpython-311.pyc b/litellm/__pycache__/main.cpython-311.pyc
index d7f053f664c..adb45149c93 100644
Binary files a/litellm/__pycache__/main.cpython-311.pyc and b/litellm/__pycache__/main.cpython-311.pyc differ
diff --git a/litellm/integrations/__pycache__/supabase.cpython-311.pyc b/litellm/integrations/__pycache__/supabase.cpython-311.pyc
index ffb30cda564..ffc824e92a5 100644
Binary files a/litellm/integrations/__pycache__/supabase.cpython-311.pyc and b/litellm/integrations/__pycache__/supabase.cpython-311.pyc differ
diff --git a/litellm/tests/test_streaming.py b/litellm/tests/test_streaming.py
index e5b9c3993ef..d37cc1c4ef8 100644
--- a/litellm/tests/test_streaming.py
+++ b/litellm/tests/test_streaming.py
@@ -1,7 +1,7 @@
 #### What this tests ####
 #    This tests streaming for the completion endpoint
 
-import sys, os
+import sys, os, asyncio
 import traceback
 import time
 
@@ -102,6 +102,27 @@ def test_openai_chat_completion_call():
         print(f"error occurred: {traceback.format_exc()}")
         pass
 
+async def completion_call():
+    try:
+        response = completion(
+            model="gpt-3.5-turbo", messages=messages, stream=True, logger_fn=logger_fn
+        )
+        print(f"response: {response}")
+        complete_response = ""
+        start_time = time.time()
+        # Change for loop to async for loop
+        async for chunk in response:
+            chunk_time = time.time()
+            print(f"time since initial request: {chunk_time - start_time:.5f}")
+            print(chunk["choices"][0]["delta"])
+            complete_response += chunk["choices"][0]["delta"]["content"]
+        if complete_response == "": 
+            raise Exception("Empty response received")
+    except:
+        print(f"error occurred: {traceback.format_exc()}")
+        pass
+
+asyncio.run(completion_call())
 
 # # test on azure completion call
 # try:
@@ -191,7 +212,7 @@ def test_together_ai_completion_call_starcoder():
         print(f"error occurred: {traceback.format_exc()}")
         pass
 
-# test on aleph alpha completion call
+# test on aleph alpha completion call - commented out as it's expensive to run this on circle ci for every build
 # def test_aleph_alpha_call():
 #     try:
 #         start_time = time.time()