diff --git a/server/llm_utils.py b/server/llm_utils.py
index 8f94692..d2cbaf6 100644
--- a/server/llm_utils.py
+++ b/server/llm_utils.py
@@ -5,9 +5,12 @@
 from openai import OpenAI
 
 
-model_name = "qwen2.5-72b-instruct"                             # qwen-plus, 模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
-url = "https://dashscope.aliyuncs.com/compatible-mode/v1"
-api_key = ""                                                    # 阿里云 API Key
+model_name = "gemini-1.5-flash"                             # gemini model; 更多参考：https://ai.google.dev/gemini-api/docs/models/gemini-v2?hl=zh-cn
+api_key = ""                                                    # Gemini API Key
+url = "https://generativelanguage.googleapis.com/v1beta/"
+# model_name = "qwen2.5-72b-instruct"                             # qwen-plus, 模型列表：https://help.aliyun.com/zh/model-studio/getting-started/models
+# url = "https://dashscope.aliyuncs.com/compatible-mode/v1"
+# api_key = ""                                                    # 阿里云 API Key
 
 
 class LLMClient(object):
@@ -17,7 +20,7 @@ def get_response_by_api(
         prompt: str,   
     ) -> str:
         messages = [
-            {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
+            {"role": "system", "content": "You are Gemini, created by Google. You are a helpful assistant."},
             {"role": "user", "content": prompt}
         ]
         client = OpenAI(
@@ -53,4 +56,4 @@ def walk_to_random_item(
 
 if __name__ == "__main__":
     res = LLMClient.get_response_by_api("你好")
-    print(res)
\ No newline at end of file
+    print(res)