diff --git a/litellm/caching/caching.py b/litellm/caching/caching.py
index b35ea2d5db6..89208159bf0 100644
--- a/litellm/caching/caching.py
+++ b/litellm/caching/caching.py
@@ -94,7 +94,7 @@ def _request_message_count(kwargs: Mapping[str, object]) -> int:
     return sum(1 for item in items if _is_conversation_item(item))
 
 
-def _is_cache_call_type_supported(call_type: str, supported_call_types: Sequence[str] | None) -> bool:
+def is_cache_call_type_supported(call_type: str, supported_call_types: Sequence[str] | None) -> bool:
     if supported_call_types is None:
         return True
     normalised_call_type: Final = call_type.lstrip("_")
@@ -994,7 +994,7 @@ class Cache:
             if raw_source is not None:
                 raw_name: Final[object] = getattr(raw_source, "value", None) or getattr(raw_source, "__name__", None)
                 call_type_name: Final = raw_name if isinstance(raw_name, str) else str(raw_source)
-                if not _is_cache_call_type_supported(call_type_name, self.supported_call_types):
+                if not is_cache_call_type_supported(call_type_name, self.supported_call_types):
                     return False
         if self.max_messages is not None and _request_message_count(kwargs) > self.max_messages:
             return False
diff --git a/litellm/caching/caching_handler.py b/litellm/caching/caching_handler.py
index 44ee31d727c..38c4b9cb391 100644
--- a/litellm/caching/caching_handler.py
+++ b/litellm/caching/caching_handler.py
@@ -27,7 +27,7 @@ import litellm
 from litellm._internal_context import is_internal_call, post_response_phase
 from litellm._logging import print_verbose, verbose_logger
 from litellm.caching import InMemoryCache
-from litellm.caching.caching import S3Cache, _is_cache_call_type_supported, response_cache_phase
+from litellm.caching.caching import S3Cache, is_cache_call_type_supported, response_cache_phase
 from litellm.constants import CACHE_WRITE_SHUTDOWN_FLUSH_TIMEOUT_SECONDS, RESPONSE_CACHE_EXCLUDED_PROVIDERS
 from litellm.litellm_core_utils.hidden_params import get_hidden_params
 from litellm.litellm_core_utils.llm_response_utils.response_metadata import (
@@ -1292,7 +1292,7 @@ class LLMCachingHandler:
         """
         if litellm.cache is None:
             return False
-        return _is_cache_call_type_supported(original_function.__name__, litellm.cache.supported_call_types)
+        return is_cache_call_type_supported(original_function.__name__, litellm.cache.supported_call_types)
 
     async def add_streaming_response_to_cache(self, processed_chunk: ModelResponse) -> None:
         """