diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py
index df025949530..4710cb8c926 100644
--- a/litellm/litellm_core_utils/litellm_logging.py
+++ b/litellm/litellm_core_utils/litellm_logging.py
@@ -1315,7 +1315,7 @@ class Logging:
                 verbose_logger.debug(
                     f"Model={self.model}; cost={self.model_call_details['response_cost']}"
                 )
-            except litellm.NotFoundError as e:
+            except litellm.NotFoundError:
                 verbose_logger.warning(
                     f"Model={self.model} not found in completion cost map. Setting 'response_cost' to None"
                 )
diff --git a/litellm/proxy/_new_secret_config.yaml b/litellm/proxy/_new_secret_config.yaml
index b81f6abde9a..62faafe0e85 100644
--- a/litellm/proxy/_new_secret_config.yaml
+++ b/litellm/proxy/_new_secret_config.yaml
@@ -1,4 +1,15 @@
 model_list:
-  - model_name: "ollama-llama3.1"
+  - model_name: gpt-3.5-turbo
     litellm_params:
-      model: "ollama_chat/llama3.1"
\ No newline at end of file
+      model: gpt-3.5-turbo
+
+litellm_settings:
+  cache: True          # set cache responses to True
+  cache_params:        # set cache params for s3
+    type: s3
+    s3_bucket_name: litellm-proxy   # AWS Bucket Name for S3
+    s3_region_name: us-west-2              # AWS Region Name for S3
+    s3_aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID  # us os.environ/<variable name> to pass environment variables. This is AWS Access Key ID for S3
+    s3_aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY  # AWS Secret Access Key for S3
+
+
diff --git a/litellm/tests/test_caching.py b/litellm/tests/test_caching.py
index ee8b0535401..89b83bcd664 100644
--- a/litellm/tests/test_caching.py
+++ b/litellm/tests/test_caching.py
@@ -1033,11 +1033,10 @@ def test_disk_cache_completion():
     assert response1.choices[0].message.content == response2.choices[0].message.content
 
 
-@pytest.mark.skip(reason="AWS Suspended Account")
+# @pytest.mark.skip(reason="AWS Suspended Account")
+@pytest.mark.parametrize("sync_mode", [True, False])
 @pytest.mark.asyncio
-async def test_s3_cache_acompletion_stream_azure():
-    import asyncio
-
+async def test_s3_cache_stream_azure(sync_mode):
     try:
         litellm.set_verbose = True
         random_word = generate_random_word()
@@ -1049,8 +1048,8 @@ async def test_s3_cache_acompletion_stream_azure():
         ]
         litellm.cache = Cache(
             type="s3",
-            s3_bucket_name="litellm-my-test-bucket-2",
-            s3_region_name="us-east-1",
+            s3_bucket_name="litellm-proxy",
+            s3_region_name="us-west-2",
         )
         print("s3 Cache: test for caching, streaming + completion")
         response_1_content = ""
@@ -1059,34 +1058,65 @@ async def test_s3_cache_acompletion_stream_azure():
         response_1_created = ""
         response_2_created = ""
 
-        response1 = await litellm.acompletion(
-            model="azure/chatgpt-v-2",
-            messages=messages,
-            max_tokens=40,
-            temperature=1,
-            stream=True,
-        )
-        async for chunk in response1:
-            print(chunk)
-            response_1_created = chunk.created
-            response_1_content += chunk.choices[0].delta.content or ""
-        print(response_1_content)
+        if sync_mode:
+            response1 = litellm.completion(
+                model="azure/chatgpt-v-2",
+                messages=messages,
+                max_tokens=40,
+                temperature=1,
+                stream=True,
+            )
+            for chunk in response1:
+                print(chunk)
+                response_1_created = chunk.created
+                response_1_content += chunk.choices[0].delta.content or ""
+            print(response_1_content)
+        else:
+            response1 = await litellm.acompletion(
+                model="azure/chatgpt-v-2",
+                messages=messages,
+                max_tokens=40,
+                temperature=1,
+                stream=True,
+            )
+            async for chunk in response1:
+                print(chunk)
+                response_1_created = chunk.created
+                response_1_content += chunk.choices[0].delta.content or ""
+            print(response_1_content)
 
-        time.sleep(0.5)
+        if sync_mode:
+            time.sleep(0.5)
+        else:
+            await asyncio.sleep(0.5)
         print("\n\n Response 1 content: ", response_1_content, "\n\n")
 
-        response2 = await litellm.acompletion(
-            model="azure/chatgpt-v-2",
-            messages=messages,
-            max_tokens=40,
-            temperature=1,
-            stream=True,
-        )
-        async for chunk in response2:
-            print(chunk)
-            response_2_content += chunk.choices[0].delta.content or ""
-            response_2_created = chunk.created
-        print(response_2_content)
+        if sync_mode:
+            response2 = litellm.completion(
+                model="azure/chatgpt-v-2",
+                messages=messages,
+                max_tokens=40,
+                temperature=1,
+                stream=True,
+            )
+            for chunk in response2:
+                print(chunk)
+                response_2_content += chunk.choices[0].delta.content or ""
+                response_2_created = chunk.created
+            print(response_2_content)
+        else:
+            response2 = await litellm.acompletion(
+                model="azure/chatgpt-v-2",
+                messages=messages,
+                max_tokens=40,
+                temperature=1,
+                stream=True,
+            )
+            async for chunk in response2:
+                print(chunk)
+                response_2_content += chunk.choices[0].delta.content or ""
+                response_2_created = chunk.created
+            print(response_2_content)
 
         print("\nresponse 1", response_1_content)
         print("\nresponse 2", response_2_content)