diff --git a/docs/my-website/docs/completion/stream.md b/docs/my-website/docs/completion/stream.md
index e5fa50ab5a..b954e60ad1 100644
--- a/docs/my-website/docs/completion/stream.md
+++ b/docs/my-website/docs/completion/stream.md
@@ -30,4 +30,42 @@ async def test_get_response():
 response = asyncio.run(test_get_response())
 print(response)
 
+```
+
+## Async Streaming
+We've implemented an `__anext__()` function in the streaming object returned. This 
+### Usage
+```
+from litellm import acompletion
+import asyncio
+
+def logger_fn(model_call_object: dict):
+    print(f"LOGGER FUNCTION: {model_call_object}")
+
+
+user_message = "Hello, how are you?"
+messages = [{"content": user_message, "role": "user"}]
+
+# # test on ai21 completion call
+async def ai21_async_completion_call():
+    try:
+        response = completion(
+            model="j2-ultra", 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(ai21_async_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 1417494660..a95ce65c85 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 3b9ce290a9..d7f053f664 100644
Binary files a/litellm/__pycache__/main.cpython-311.pyc and b/litellm/__pycache__/main.cpython-311.pyc differ
diff --git a/litellm/__pycache__/utils.cpython-311.pyc b/litellm/__pycache__/utils.cpython-311.pyc
index 56b13fe11a..538c697581 100644
Binary files a/litellm/__pycache__/utils.cpython-311.pyc and b/litellm/__pycache__/utils.cpython-311.pyc differ
diff --git a/litellm/tests/test_streaming.py b/litellm/tests/test_streaming.py
index 90828d20cb..e5b9c3993e 100644
--- a/litellm/tests/test_streaming.py
+++ b/litellm/tests/test_streaming.py
@@ -9,7 +9,7 @@ sys.path.insert(
     0, os.path.abspath("../..")
 )  # Adds the parent directory to the system path
 import litellm
-from litellm import completion
+from litellm import completion, acompletion
 
 litellm.logging = False
 litellm.set_verbose = False
@@ -217,3 +217,25 @@ def test_together_ai_completion_call_starcoder():
 #     except:
 #         print(f"error occurred: {traceback.format_exc()}")
 #         pass
+#### Test Async streaming 
+
+# # test on ai21 completion call
+async def ai21_async_completion_call():
+    try:
+        response = completion(
+            model="j2-ultra", 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
\ No newline at end of file