From 6a96b6c264e9ce19ee4584e07b2493ba5b873104 Mon Sep 17 00:00:00 2001
From: Sumit Jaiswal <sjaiswal@redhat.com>
Date: Fri, 30 May 2025 00:23:56 +0530
Subject: [PATCH] update the API

---
 llama_stack/providers/remote/inference/vllm/vllm.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/llama_stack/providers/remote/inference/vllm/vllm.py b/llama_stack/providers/remote/inference/vllm/vllm.py
index ea972a1b7..49a0b96bc 100644
--- a/llama_stack/providers/remote/inference/vllm/vllm.py
+++ b/llama_stack/providers/remote/inference/vllm/vllm.py
@@ -316,7 +316,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
             client = self._create_client() if self.client is None else self.client
             if client.api_key:
                 headers["Authorization"] = f"Bearer {client.api_key}"
-            models_url = f"{client.base_url}/v1/models"
+            models_url = f"{client.base_url}models"
             requests.get(models_url, headers=headers, timeout=10)
             return HealthResponse(
                 status=HealthStatus.OK