added import aiohttp

litellm/utils.py

@@ -6,6 +6,7 @@ import random, uuid, requests
 import datetime, time
 import tiktoken
 import uuid
+import aiohttp
 
 encoding = tiktoken.get_encoding("cl100k_base")
 import importlib.metadata
@@ -2322,4 +2323,4 @@ def completion_with_fallbacks(**kwargs):
                 )  # cool down this selected model
                 # print(f"rate_limited_models {rate_limited_models}")
                 pass
-    return response
+    return response