diff --git a/litellm/llms/vertex_ai/count_tokens/handler.py b/litellm/llms/vertex_ai/count_tokens/handler.py
index 1fc0ff9a031..47a08ff054d 100644
--- a/litellm/llms/vertex_ai/count_tokens/handler.py
+++ b/litellm/llms/vertex_ai/count_tokens/handler.py
@@ -20,7 +20,6 @@ class VertexAITokenCounter(GoogleAIStudioTokenCounter, VertexBase):
         vertex_credentials: Final = self.get_vertex_ai_credentials(litellm_params=litellm_params)
         vertex_project = self.get_vertex_ai_project(litellm_params=litellm_params)
         vertex_location: Final = self.get_vertex_ai_location(litellm_params=litellm_params)
-        should_use_v1beta1_features: Final = self.is_using_v1beta1_features(litellm_params)
         _auth_header, vertex_project = await self._ensure_access_token_async(
             credentials=vertex_credentials,
             project_id=vertex_project,
@@ -37,7 +36,6 @@ class VertexAITokenCounter(GoogleAIStudioTokenCounter, VertexBase):
             stream=False,
             custom_llm_provider="vertex_ai",
             api_base=None,
-            should_use_v1beta1_features=should_use_v1beta1_features,
             mode="count_tokens",
         )
         headers = {
diff --git a/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py b/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
index 36b5f2fb5e8..e8b316b5902 100644
--- a/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
+++ b/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
@@ -2701,8 +2701,6 @@ class VertexLLM(VertexBase):
         gemini_api_key: str | None = None,
         extra_headers: dict | None = None,
     ) -> CustomStreamWrapper:
-        should_use_v1beta1_features: Final = self.is_using_v1beta1_features(optional_params=optional_params)
-
         _auth_header, vertex_project = await self._ensure_access_token_async(
             credentials=vertex_credentials,
             project_id=vertex_project,
@@ -2722,7 +2720,6 @@ class VertexLLM(VertexBase):
             stream=stream,
             custom_llm_provider=custom_llm_provider,
             api_base=api_base,
-            should_use_v1beta1_features=should_use_v1beta1_features,
             use_psc_endpoint_format=use_psc_endpoint_format,
         )
 
@@ -2797,8 +2794,6 @@ class VertexLLM(VertexBase):
         gemini_api_key: str | None = None,
         extra_headers: dict | None = None,
     ) -> ModelResponse | CustomStreamWrapper:
-        should_use_v1beta1_features: Final = self.is_using_v1beta1_features(optional_params=optional_params)
-
         _auth_header, vertex_project = await self._ensure_access_token_async(
             credentials=vertex_credentials,
             project_id=vertex_project,
@@ -2818,7 +2813,6 @@ class VertexLLM(VertexBase):
             stream=stream,
             custom_llm_provider=custom_llm_provider,
             api_base=api_base,
-            should_use_v1beta1_features=should_use_v1beta1_features,
             use_psc_endpoint_format=use_psc_endpoint_format,
         )
 
@@ -2981,8 +2975,6 @@ class VertexLLM(VertexBase):
                 extra_headers=extra_headers,
             )
 
-        should_use_v1beta1_features: Final = self.is_using_v1beta1_features(optional_params=optional_params)
-
         _auth_header, vertex_project = self._ensure_access_token(
             credentials=vertex_credentials,
             project_id=vertex_project,
@@ -3002,7 +2994,6 @@ class VertexLLM(VertexBase):
             stream=stream,
             custom_llm_provider=custom_llm_provider,
             api_base=api_base,
-            should_use_v1beta1_features=should_use_v1beta1_features,
             use_psc_endpoint_format=use_psc_endpoint_format,
         )
         headers: Final = VertexGeminiConfig().validate_environment(
diff --git a/litellm/llms/vertex_ai/vertex_embeddings/embedding_handler.py b/litellm/llms/vertex_ai/vertex_embeddings/embedding_handler.py
index 81961d6ef8b..15378839b33 100644
--- a/litellm/llms/vertex_ai/vertex_embeddings/embedding_handler.py
+++ b/litellm/llms/vertex_ai/vertex_embeddings/embedding_handler.py
@@ -65,8 +65,6 @@ class VertexEmbedding(VertexBase):
                 litellm_params=litellm_params,
             )
 
-        should_use_v1beta1_features: Final = self.is_using_v1beta1_features(optional_params=optional_params)
-
         _auth_header, vertex_project = self._ensure_access_token(
             credentials=vertex_credentials,
             project_id=vertex_project,
@@ -85,7 +83,6 @@ class VertexEmbedding(VertexBase):
             stream=False,
             custom_llm_provider=custom_llm_provider,
             api_base=api_base,
-            should_use_v1beta1_features=should_use_v1beta1_features,
             mode="embedding",
             use_psc_endpoint_format=use_psc_endpoint_format,
         )
@@ -160,7 +157,6 @@ class VertexEmbedding(VertexBase):
         """
         Async embedding implementation
         """
-        should_use_v1beta1_features: Final = self.is_using_v1beta1_features(optional_params=optional_params)
         _auth_header, vertex_project = await self._ensure_access_token_async(
             credentials=vertex_credentials,
             project_id=vertex_project,
@@ -179,7 +175,6 @@ class VertexEmbedding(VertexBase):
             stream=False,
             custom_llm_provider=custom_llm_provider,
             api_base=api_base,
-            should_use_v1beta1_features=should_use_v1beta1_features,
             mode="embedding",
             use_psc_endpoint_format=use_psc_endpoint_format,
         )
diff --git a/litellm/llms/vertex_ai/vertex_llm_base.py b/litellm/llms/vertex_ai/vertex_llm_base.py
index 1942bc850f1..8b7f8c63625 100644
--- a/litellm/llms/vertex_ai/vertex_llm_base.py
+++ b/litellm/llms/vertex_ai/vertex_llm_base.py
@@ -618,15 +618,6 @@ class VertexBase:
                 project_id=project_id,
             )
 
-    def is_using_v1beta1_features(self, optional_params: dict) -> bool:
-        """
-        use this helper to decide if request should be sent to v1 or v1beta1
-
-        Returns true if any beta feature is enabled
-        Returns false in all other cases
-        """
-        return False
-
     def _check_custom_proxy(
         self,
         api_base: str | None,
diff --git a/tests/test_litellm/llms/vertex_ai/test_vertex_ai_common_utils.py b/tests/test_litellm/llms/vertex_ai/test_vertex_ai_common_utils.py
index c206fcec420..7d2dfbb962e 100644
--- a/tests/test_litellm/llms/vertex_ai/test_vertex_ai_common_utils.py
+++ b/tests/test_litellm/llms/vertex_ai/test_vertex_ai_common_utils.py
@@ -1150,10 +1150,6 @@ def test_get_token_url():
     vertex_ai_location = "us-central1"
     vertex_credentials = ""
 
-    should_use_v1beta1_features = vertex_llm.is_using_v1beta1_features(
-        optional_params={"cached_content": "hi"}
-    )
-
     _, url = vertex_llm._get_token_and_url(
         auth_header=None,
         vertex_project=vertex_ai_project,
@@ -1161,7 +1157,7 @@ def test_get_token_url():
         vertex_credentials=vertex_credentials,
         gemini_api_key="",
         custom_llm_provider="vertex_ai_beta",
-        should_use_v1beta1_features=should_use_v1beta1_features,
+        should_use_v1beta1_features=False,
         api_base=None,
         model="",
         stream=False,
@@ -1169,10 +1165,6 @@ def test_get_token_url():
 
     print("url=", url)
 
-    should_use_v1beta1_features = vertex_llm.is_using_v1beta1_features(
-        optional_params={"temperature": 0.1}
-    )
-
     _, url = vertex_llm._get_token_and_url(
         auth_header=None,
         vertex_project=vertex_ai_project,
@@ -1180,7 +1172,7 @@ def test_get_token_url():
         vertex_credentials=vertex_credentials,
         gemini_api_key="",
         custom_llm_provider="vertex_ai_beta",
-        should_use_v1beta1_features=should_use_v1beta1_features,
+        should_use_v1beta1_features=False,
         api_base=None,
         model="",
         stream=False,