diff --git a/litellm/tests/test_async_fn.py b/litellm/tests/test_async_fn.py
index cd459dc1d..920b7524e 100644
--- a/litellm/tests/test_async_fn.py
+++ b/litellm/tests/test_async_fn.py
@@ -47,6 +47,7 @@ def test_async_response_openai():
         try:
             response = await acompletion(model="gpt-3.5-turbo", messages=messages, timeout=5)
             print(f"response: {response}")
+            print(f"response ms: {response._response_ms}")
         except litellm.Timeout as e: 
             pass
         except Exception as e:
@@ -55,7 +56,7 @@ def test_async_response_openai():
 
     asyncio.run(test_get_response())
 
-# test_async_response_openai()
+test_async_response_openai()
 
 def test_async_response_azure():
     import asyncio
@@ -160,4 +161,4 @@ def test_get_response_non_openai_streaming():
         return response
     asyncio.run(test_async_call())
 
-test_get_response_non_openai_streaming()
\ No newline at end of file
+# test_get_response_non_openai_streaming()
\ No newline at end of file
diff --git a/litellm/utils.py b/litellm/utils.py
index ac8c9d8d2..10601b653 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -1370,6 +1370,8 @@ def client(original_function):
             # LOG SUCCESS - handle streaming success logging in the _next_ object, remove `handle_success` once it's deprecated
             threading.Thread(target=logging_obj.success_handler, args=(result, start_time, end_time)).start()
             # RETURN RESULT
+            if isinstance(result, ModelResponse):
+                result._response_ms = (end_time - start_time).total_seconds() * 1000 # return response latency in ms like openai
             return result
         except Exception as e: 
             call_type = original_function.__name__