diff --git a/litellm/utils.py b/litellm/utils.py
index ac26e08640d..9367db74b1b 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -4192,7 +4192,14 @@ def get_optional_params(
                 optional_params["stop_sequences"] = stop
         if max_tokens is not None:
             optional_params["max_output_tokens"] = max_tokens
-    elif custom_llm_provider == "vertex_ai":
+    elif custom_llm_provider == "vertex_ai" and model in (
+        litellm.vertex_chat_models
+        or model in litellm.vertex_code_chat_models
+        or model in litellm.vertex_text_models
+        or model in litellm.vertex_code_text_models
+        or model in litellm.vertex_language_models
+        or model in litellm.vertex_embedding_models
+    ):
         ## check if unsupported param passed in
         supported_params = [
             "temperature",