diff --git a/litellm/__pycache__/utils.cpython-311.pyc b/litellm/__pycache__/utils.cpython-311.pyc
index c9511669f9a..734fe46bb77 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_completion.py b/litellm/tests/test_completion.py
index 0e995cd9c30..5368dafc7ea 100644
--- a/litellm/tests/test_completion.py
+++ b/litellm/tests/test_completion.py
@@ -791,7 +791,8 @@ def test_completion_ai21():
     try:
         response = completion(model=model_name, messages=messages)
         # Add any assertions here to check the response
-        print(response)
+        print(response["response_ms"])
+        print(response.response_ms)
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
diff --git a/litellm/utils.py b/litellm/utils.py
index 89b09206025..a974fc8bb3d 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -123,7 +123,7 @@ class StreamingChoices(OpenAIObject):
             self.delta = Delta()
 
 class ModelResponse(OpenAIObject):
-    def __init__(self, id=None, choices=None, created=None, model=None, usage=None, stream=False, **params):
+    def __init__(self, id=None, choices=None, created=None, model=None, usage=None, stream=False, response_ms=None, **params):
         if stream:
             self.object = "chat.completion.chunk"
             self.choices = [StreamingChoices()]
@@ -141,6 +141,10 @@ class ModelResponse(OpenAIObject):
             self.created = int(time.time())
         else:
             self.created = created
+        if response_ms:
+            response_ms = response_ms
+        else:
+            response_ms = None
         self.model = model
         self.usage = (
             usage
@@ -624,6 +628,7 @@ def client(original_function):
             )  # don't interrupt execution of main thread
             my_thread.start()
             # RETURN RESULT
+            result.response_ms = (end_time - start_time).total_seconds() * 1000 # return response latency in ms like openai
             return result
         except Exception as e:
             traceback_exception = traceback.format_exc()
diff --git a/pyproject.toml b/pyproject.toml
index b8de7bb568e..707d9ac0b6a 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.717"
+version = "0.1.718"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"