diff --git a/ochat/serving/openai_api_protocol.py b/ochat/serving/openai_api_protocol.py
index 139e058..bfe5750 100644
--- a/ochat/serving/openai_api_protocol.py
+++ b/ochat/serving/openai_api_protocol.py
@@ -59,7 +59,7 @@ class ChatCompletionRequest(BaseModel):
     top_p: Optional[float] = 1.0
     n: Optional[int] = 1
     max_tokens: Optional[int] = 768
-    stop: Optional[Union[str, List[str]]] = Field(default_factory=list)
+    stop: Optional[Union[str, List[str]]] = None
     stream: Optional[bool] = False
     presence_penalty: Optional[float] = 0.0
     frequency_penalty: Optional[float] = 0.0
diff --git a/ochat/serving/openai_api_server.py b/ochat/serving/openai_api_server.py
index 4645c67..b92c717 100644
--- a/ochat/serving/openai_api_server.py
+++ b/ochat/serving/openai_api_server.py
@@ -160,7 +160,7 @@ async def create_chat_completion(raw_request: Request):
             frequency_penalty=request.frequency_penalty,
             temperature=request.temperature,
             top_p=request.top_p,
-            stop=[model.eot_token],
+            stop=request.stop,
             max_tokens=request.max_tokens
         )
     except ValueError as e: