diff --git a/litellm/llms/vllm/common_utils.py b/litellm/llms/vllm/common_utils.py
index 2da2269e1f9..f663ec7870a 100644
--- a/litellm/llms/vllm/common_utils.py
+++ b/litellm/llms/vllm/common_utils.py
@@ -47,9 +47,7 @@ class VLLMModelInfo(BaseLLMModelInfo):
     def get_api_base(api_base: str | None = None) -> str | None:
         api_base = api_base or get_secret_str("VLLM_API_BASE")
         if api_base is None:
-            raise ValueError(
-                "VLLM_API_BASE is not set. Please set the environment variable, to use VLLM's pass-through - `{LITELLM_API_BASE}/vllm/{endpoint}`."
-            )
+            raise ValueError("VLLM_API_BASE is not set.")
         return api_base
 
     @staticmethod
@@ -62,12 +60,7 @@ class VLLMModelInfo(BaseLLMModelInfo):
 
     def get_models(self, api_key: str | None = None, api_base: str | None = None) -> list[str]:
         api_base = VLLMModelInfo.get_api_base(api_base)
-        api_key = VLLMModelInfo.get_api_key(api_key)
         endpoint: Final = "/v1/models"
-        if api_base is None or api_key is None:
-            raise ValueError(
-                "VLLM_API_BASE or VLLM_API_KEY is not set. Please set the environment variable, to query VLLM's `/models` endpoint."
-            )
 
         url: Final = _add_path_to_api_base(api_base, endpoint)
         response: Final = litellm.module_level_client.get(
diff --git a/tests/test_litellm/proxy/auth/test_model_checks.py b/tests/test_litellm/proxy/auth/test_model_checks.py
index f580df2dad6..451f4eac9a0 100644
--- a/tests/test_litellm/proxy/auth/test_model_checks.py
+++ b/tests/test_litellm/proxy/auth/test_model_checks.py
@@ -449,10 +449,6 @@ def test_get_known_models_from_wildcard_hosted_vllm_uses_provider_endpoint():
         litellm.check_provider_endpoint = True  # test-quality-ok: required to exercise provider endpoint discovery
         with (
             patch("litellm.module_level_client.get", return_value=response),  # test-quality-ok: required HTTP boundary
-            patch(  # test-quality-ok: VLLM model listing has no injectable API key seam
-                "litellm.llms.vllm.common_utils.VLLMModelInfo.get_api_key",
-                return_value="test-key",
-            ),
         ):
             result = get_known_models_from_wildcard(
                 "hosted_vllm/*",