diff --git a/litellm/caching.py b/litellm/caching.py
index a0aa1e3ffb8..921ae1b21ac 100644
--- a/litellm/caching.py
+++ b/litellm/caching.py
@@ -119,9 +119,6 @@ class RedisCache(BaseCache):
 
         # for high traffic, we store the redis results in memory and then batch write to redis
         self.redis_batch_writing_buffer = []
-        self.redis_batch_reading_buffer = []
-        self.redis_last_updated_read_buffer = None
-        self.redis_fetch_interval = 1  # fetch from redis every 1 second
         self.redis_flush_size = redis_flush_size
         self.redis_version = "Unknown"
         try:
@@ -256,24 +253,11 @@ class RedisCache(BaseCache):
             traceback.print_exc()
             logging.debug("LiteLLM Caching: get() - Got exception from REDIS: ", e)
 
-    def _should_fetch_from_redis(self):
-        if self.redis_last_updated_read_buffer is None:
-            return True
-        if (
-            time.time() - self.redis_last_updated_read_buffer
-            > self.redis_fetch_interval
-        ):
-            return True
-        return False
-
     async def async_get_cache(self, key, **kwargs):
         _redis_client = self.init_async_client()
         async with _redis_client as redis_client:
             try:
                 print_verbose(f"Get Async Redis Cache: key: {key}")
-                if self._should_fetch_from_redis():
-                    self.redis_last_updated_read_buffer = time.time()
-
                 cached_response = await redis_client.get(key)
                 print_verbose(
                     f"Got Async Redis Cache: key: {key}, cached_response {cached_response}"
diff --git a/litellm/utils.py b/litellm/utils.py
index b094db987cb..1df945ac72e 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -2814,21 +2814,18 @@ def client(original_function):
             )
             # if caching is false, don't run this
             final_embedding_cached_response = None
-            cache_controls = kwargs.get("cache", None)
-
-            # Check if user has opted out of caching
-            _opted_out_with_cache_controls = (
-                cache_controls and cache_controls.get("no-cache", False) == True
-            )
-            _opted_out_with_caching_param = kwargs.get("caching", True) == False
-
-            # cache is not None and user has not opted out
             if (
-                litellm.cache is not None
-                and (not _opted_out_with_cache_controls)
-                and (not _opted_out_with_caching_param)
-            ):
-                # allow users to control returning cached responses from the completion function
+                (
+                    kwargs.get("caching", None) is None
+                    and kwargs.get("cache", None) is None
+                    and litellm.cache is not None
+                )
+                or kwargs.get("caching", False) == True
+                or (
+                    kwargs.get("cache", None) is not None
+                    and kwargs.get("cache").get("no-cache", False) != True
+                )
+            ):  # allow users to control returning cached responses from the completion function
                 # checking cache
                 print_verbose(f"INSIDE CHECKING CACHE")
                 if (