diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/credential/image.py b/apps/models_provider/impl/aliyun_bai_lian_model_provider/credential/image.py
index 13f32ebb6..444b1ff2f 100644
--- a/apps/models_provider/impl/aliyun_bai_lian_model_provider/credential/image.py
+++ b/apps/models_provider/impl/aliyun_bai_lian_model_provider/credential/image.py
@@ -67,9 +67,7 @@ class QwenVLModelCredential(BaseForm, BaseModelCredential):
 
         try:
             model = provider.get_model(model_type, model_name, model_credential, **model_params)
-            res = model.stream([HumanMessage(content=[{"type": "text", "text": gettext('Hello')}])])
-            for chunk in res:
-                maxkb_logger.info(chunk)
+            model.check_auth(model_credential.get('api_key'))
         except Exception as e:
             traceback.print_exc()
             if isinstance(e, AppApiException):
diff --git a/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/image.py b/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/image.py
index 1d63c44c1..a03cccfa3 100644
--- a/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/image.py
+++ b/apps/models_provider/impl/aliyun_bai_lian_model_provider/model/image.py
@@ -2,6 +2,9 @@
 
 from typing import Dict
 
+from langchain_community.chat_models import ChatTongyi
+from langchain_core.messages import HumanMessage
+from django.utils.translation import gettext
 from models_provider.base_model_provider import MaxKBBaseModel
 from models_provider.impl.base_chat_open_ai import BaseChatOpenAI
 
@@ -25,3 +28,7 @@ class QwenVLChatModel(MaxKBBaseModel, BaseChatOpenAI):
             extra_body=optional_params
         )
         return chat_tong_yi
+
+    def check_auth(self, api_key):
+        chat = ChatTongyi(api_key=api_key, model_name='qwen-max')
+        chat.invoke([HumanMessage([{"type": "text", "text": gettext('Hello')}])])