diff --git a/litellm/tests/test_cache.py b/litellm/tests/test_cache.py
index 40be3b9a53..1d3f8cdc3f 100644
--- a/litellm/tests/test_cache.py
+++ b/litellm/tests/test_cache.py
@@ -3,10 +3,10 @@ import traceback
 from dotenv import load_dotenv
 load_dotenv()
 import os
+
 sys.path.insert(0, os.path.abspath('../..'))  # Adds the parent directory to the system path
 import pytest
 import litellm
-from litellm import embedding, completion
 
 # set cache to True
 litellm.cache = True
@@ -15,19 +15,20 @@ litellm.cache_similarity_threshold = 0.5
 user_message = "Hello, whats the weather in San Francisco??"
 messages = [{ "content": user_message,"role": "user"}]
 
-def test_completion_gpt():
+def test_completion_with_cache_gpt4():
     try:
         # in this test make the same call twice, measure the response time
         # the 2nd response time should be less than half of the first, ensuring that the cache is working
         import time
         start = time.time()
-        response = completion(model="gpt-4", messages=messages)
+        print(litellm.cache)
+        response = litellm.completion(model="gpt-4", messages=messages)
         end = time.time()
         first_call_time = end-start
         print(f"first call: {first_call_time}")
 
         start = time.time()
-        response = completion(model="gpt-4", messages=messages)
+        response = litellm.completion(model="gpt-4", messages=messages)
         end = time.time()
         second_call_time = end-start
         print(f"second call: {second_call_time}")
@@ -40,5 +41,3 @@ def test_completion_gpt():
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
-
-litellm.cache = False # rest to False for the next test
\ No newline at end of file