diff --git a/pilot/configs/config.py b/pilot/configs/config.py
index 9023bc061..b914390f7 100644
--- a/pilot/configs/config.py
+++ b/pilot/configs/config.py
@@ -105,7 +105,8 @@ class Config(metaclass=Singleton):
         self.LLM_MODEL = os.getenv("LLM_MODEL",  "vicuna-13b")
         self.LIMIT_MODEL_CONCURRENCY = int(os.getenv("LIMIT_MODEL_CONCURRENCY",  5))
         self.MAX_POSITION_EMBEDDINGS = int(os.getenv("MAX_POSITION_EMBEDDINGS",  4096))
-        self.MODEL_SERVER = os.getenv("MODEL_SERVER",  "http://121.41.167.183:8000")
+        self.MODEL_PORT = os.getenv("MODEL_PORT",  8000)
+        self.MODEL_SERVER = os.getenv("MODEL_SERVER",  "http://127.0.0.1" + ":" + str(self.MODEL_PORT))
         self.ISLOAD_8BIT = os.getenv("ISLOAD_8BIT", "True") == "True"
 
     def set_debug_mode(self, value: bool) -> None:
diff --git a/pilot/server/llmserver.py b/pilot/server/llmserver.py
index e341cc457..e1c7556f6 100644
--- a/pilot/server/llmserver.py
+++ b/pilot/server/llmserver.py
@@ -130,4 +130,4 @@ def embeddings(prompt_request: EmbeddingRequest):
 
 
 if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", log_level="info") 
\ No newline at end of file
+    uvicorn.run(app, host="0.0.0.0", port=CFG.MODEL_PORT, log_level="info")
\ No newline at end of file