diff --git a/libraries/nxd-inference/developer_guides/vllm-user-guide.rst b/libraries/nxd-inference/developer_guides/vllm-user-guide.rst
index c56158be..42933372 100644
--- a/libraries/nxd-inference/developer_guides/vllm-user-guide.rst
+++ b/libraries/nxd-inference/developer_guides/vllm-user-guide.rst
@@ -352,7 +352,7 @@ You can change the sampling parameters and enable or disable streaming.
 
     # Client Setup
     openai_api_key = "EMPTY"
-    openai_api_base = "http://localhost:8000/v1"
+    openai_api_base = "http://localhost:8080/v1"
 
     client = OpenAI(
         api_key=openai_api_key,