diff --git a/litellm/llms/vertex_ai_and_google_ai_studio/vertex_and_google_ai_studio_gemini.py b/litellm/llms/vertex_ai_and_google_ai_studio/vertex_and_google_ai_studio_gemini.py
index d265226d023..6b87ac29e9e 100644
--- a/litellm/llms/vertex_ai_and_google_ai_studio/vertex_and_google_ai_studio_gemini.py
+++ b/litellm/llms/vertex_ai_and_google_ai_studio/vertex_and_google_ai_studio_gemini.py
@@ -1315,6 +1315,8 @@ class VertexLLM(BaseLLM):
                 cached_content=optional_params.pop("cached_content", None),
                 logging_obj=logging_obj,
             )
+        else:  # [TODO] implement context caching for gemini as well
+            cached_content = optional_params.pop("cached_content", None)
 
         # Separate system prompt from rest of message
         supports_system_message = get_supports_system_message(