diff --git a/litellm/router.py b/litellm/router.py
index 9da7488ca..e222a9336 100644
--- a/litellm/router.py
+++ b/litellm/router.py
@@ -1326,6 +1326,7 @@ class Router:
                         local_only=True,
                     )  # cache for 1 hr
 
+                    cache_key = f"{model_id}_client"
                     _client = openai.AzureOpenAI(  # type: ignore
                         api_key=api_key,
                         base_url=api_base,
diff --git a/litellm/tests/test_configs/test_cloudflare_azure_with_cache_config.yaml b/litellm/tests/test_configs/test_cloudflare_azure_with_cache_config.yaml
new file mode 100644
index 000000000..7c4f6ce24
--- /dev/null
+++ b/litellm/tests/test_configs/test_cloudflare_azure_with_cache_config.yaml
@@ -0,0 +1,7 @@
+model_list:
+  - model_name: azure-cloudflare
+    litellm_params:
+      model: azure/chatgpt-v-2
+      api_base: https://gateway.ai.cloudflare.com/v1/0399b10e77ac6668c80404a5ff49eb37/litellm-test/azure-openai/openai-gpt-4-test-v-1
+      api_key: os.environ/AZURE_API_KEY
+      api_version: 2023-07-01-preview
\ No newline at end of file
diff --git a/litellm/tests/test_proxy_server_caching.py b/litellm/tests/test_proxy_server_caching.py
index f37cd9b58..c05a244e9 100644
--- a/litellm/tests/test_proxy_server_caching.py
+++ b/litellm/tests/test_proxy_server_caching.py
@@ -1,38 +1,90 @@
-# #### What this tests ####
-# #    This tests using caching w/ litellm which requires SSL=True
+#### What this tests ####
+#    This tests using caching w/ litellm which requires SSL=True
+import sys, os
+import traceback
+from dotenv import load_dotenv
 
-# import sys, os
-# import time
-# import traceback
-# from dotenv import load_dotenv
+load_dotenv()
+import os, io
 
-# load_dotenv()
-# import os
+# this file is to test litellm/proxy
 
-# sys.path.insert(
-#     0, os.path.abspath("../..")
-# )  # Adds the parent directory to the system path
-# import pytest
-# import litellm
-# from litellm import embedding, completion
-# from litellm.caching import Cache
+sys.path.insert(
+    0, os.path.abspath("../..")
+)  # Adds the parent directory to the system path
+import pytest, logging
+import litellm
+from litellm import embedding, completion, completion_cost, Timeout
+from litellm import RateLimitError
 
-# messages = [{"role": "user", "content": f"who is ishaan {time.time()}"}]
+# Configure logging
+logging.basicConfig(
+    level=logging.DEBUG,  # Set the desired logging level
+    format="%(asctime)s - %(levelname)s - %(message)s",
+)
 
-# @pytest.mark.skip(reason="local proxy test")
-# def test_caching_v2(): # test in memory cache
-#     try:
-#         response1 = completion(model="openai/gpt-3.5-turbo", messages=messages, api_base="http://0.0.0.0:8000")
-#         response2 = completion(model="openai/gpt-3.5-turbo", messages=messages, api_base="http://0.0.0.0:8000")
-#         print(f"response1: {response1}")
-#         print(f"response2: {response2}")
-#         litellm.cache = None # disable cache
-#         if response2['choices'][0]['message']['content'] != response1['choices'][0]['message']['content']:
-#             print(f"response1: {response1}")
-#             print(f"response2: {response2}")
-#             raise Exception()
-#     except Exception as e:
-#         print(f"error occurred: {traceback.format_exc()}")
-#         pytest.fail(f"Error occurred: {e}")
+# test /chat/completion request to the proxy
+from fastapi.testclient import TestClient
+from fastapi import FastAPI
+from litellm.proxy.proxy_server import (
+    router,
+    save_worker_config,
+    initialize,
+)  # Replace with the actual module where your FastAPI router is defined
 
-# test_caching_v2()
+# Your bearer token
+token = ""
+
+headers = {"Authorization": f"Bearer {token}"}
+
+
+@pytest.fixture(scope="function")
+def client_no_auth():
+    # Assuming litellm.proxy.proxy_server is an object
+    from litellm.proxy.proxy_server import cleanup_router_config_variables
+
+    cleanup_router_config_variables()
+    filepath = os.path.dirname(os.path.abspath(__file__))
+    config_fp = f"{filepath}/test_configs/test_cloudflare_azure_with_cache_config.yaml"
+    # initialize can get run in parallel, it sets specific variables for the fast api app, sinc eit gets run in parallel different tests use the wrong variables
+    initialize(config=config_fp, debug=True)
+    app = FastAPI()
+    app.include_router(router)  # Include your router in the test app
+
+    return TestClient(app)
+
+
+def generate_random_word(length=4):
+    import string, random
+
+    letters = string.ascii_lowercase
+    return "".join(random.choice(letters) for _ in range(length))
+
+
+def test_chat_completion(client_no_auth):
+    global headers
+    try:
+        user_message = f"Write a poem about {generate_random_word()}"
+        messages = [{"content": user_message, "role": "user"}]
+        # Your test data
+        test_data = {
+            "model": "azure-cloudflare",
+            "messages": messages,
+            "max_tokens": 10,
+        }
+
+        print("testing proxy server with chat completions")
+        response = client_no_auth.post("/v1/chat/completions", json=test_data)
+        print(f"response - {response.text}")
+        assert response.status_code == 200
+
+        response = response.json()
+        print(response)
+
+        content = response["choices"][0]["message"]["content"]
+
+        print("\n content", content)
+
+        assert len(content) > 1
+    except Exception as e:
+        pytest.fail(f"LiteLLM Proxy test failed. Exception - {str(e)}")