diff --git a/litellm/caching/redis_cache.py b/litellm/caching/redis_cache.py
index af7468ba14c8..351c412e4238 100644
--- a/litellm/caching/redis_cache.py
+++ b/litellm/caching/redis_cache.py
@@ -822,7 +822,8 @@ async def async_get_cache(
             print_verbose(
                 f"Got Async Redis Cache: key: {key}, cached_response {cached_response}"
             )
-            response = self._get_cache_logic(cached_response=cached_response)
+            # Parse cached response off the event loop if it is potentially blocking (large payload etc)
+            response = await asyncio.to_thread(self._get_cache_logic, cached_response)
 
             end_time = time.time()
             _duration = end_time - start_time
diff --git a/litellm/proxy/health_check_utils/shared_health_check_manager.py b/litellm/proxy/health_check_utils/shared_health_check_manager.py
index cfd03a4d1789..befe1070b13a 100644
--- a/litellm/proxy/health_check_utils/shared_health_check_manager.py
+++ b/litellm/proxy/health_check_utils/shared_health_check_manager.py
@@ -128,7 +128,7 @@ async def get_cached_health_check_results(self) -> Optional[Dict[str, Any]]:
 
             # Parse the cached data
             if isinstance(cached_data, str):
-                cached_results = json.loads(cached_data)
+                cached_results = await asyncio.to_thread(json.loads, cached_data)
             else:
                 cached_results = cached_data