diff --git a/Dockerfile b/Dockerfile
index 7f7b119..9c365e7 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -3,10 +3,10 @@ FROM python:3.10-slim
 WORKDIR /app
 
 # 复制所需文件到容器中
-COPY ./app /app/app
 COPY ./requirements.txt /app
 
 RUN pip install --no-cache-dir -r requirements.txt
+COPY ./app /app/app
 ENV API_KEYS='["your_api_key_1"]'
 ENV ALLOWED_TOKENS='["your_token_1"]'
 ENV BASE_URL=https://generativelanguage.googleapis.com/v1beta
diff --git a/app/api/gemini_routes.py b/app/api/gemini_routes.py
index a50889a..8905257 100644
--- a/app/api/gemini_routes.py
+++ b/app/api/gemini_routes.py
@@ -63,7 +63,7 @@ async def generate_content(
     logger.info(f"Using API key: {api_key}")
 
     try:
-        response = chat_service.generate_content(
+        response = await chat_service.generate_content(
             model=model_name,
             request=request,
             api_key=api_key
@@ -122,7 +122,7 @@ async def verify_key(api_key: str):
                 )
             ]
         )
-        response = chat_service.generate_content(settings.TEST_MODEL,gemini_requset, api_key)
+        response = await chat_service.generate_content(settings.TEST_MODEL,gemini_requset, api_key)
         if response:
             return JSONResponse({"status": "valid"})
         return JSONResponse({"status": "invalid"})
diff --git a/app/services/chat/api_client.py b/app/services/chat/api_client.py
index df7f0cb..0a834d6 100644
--- a/app/services/chat/api_client.py
+++ b/app/services/chat/api_client.py
@@ -24,13 +24,13 @@ class GeminiApiClient(ApiClient):
         self.base_url = base_url
         self.timeout = timeout
 
-    def generate_content(self, payload: Dict[str, Any], model: str, api_key: str) -> Dict[str, Any]:
+    async def generate_content(self, payload: Dict[str, Any], model: str, api_key: str) -> Dict[str, Any]:
         timeout = httpx.Timeout(self.timeout, read=self.timeout)
         if model.endswith("-search"):
             model = model[:-7]
-        with httpx.Client(timeout=timeout) as client:
+        async with httpx.AsyncClient(timeout=timeout) as client:
             url = f"{self.base_url}/models/{model}:generateContent?key={api_key}"
-            response = client.post(url, json=payload)
+            response = await client.post(url, json=payload)
             if response.status_code != 200:
                 error_content = response.text
                 raise Exception(f"API call failed with status code {response.status_code}, {error_content}")
diff --git a/app/services/gemini_chat_service.py b/app/services/gemini_chat_service.py
index 48d4991..d281679 100644
--- a/app/services/gemini_chat_service.py
+++ b/app/services/gemini_chat_service.py
@@ -79,10 +79,10 @@ class GeminiChatService:
         self.key_manager = key_manager
         self.response_handler = GeminiResponseHandler()
 
-    def generate_content(self, model: str, request: GeminiRequest, api_key: str) -> Dict[str, Any]:
+    async def generate_content(self, model: str, request: GeminiRequest, api_key: str) -> Dict[str, Any]:
         """生成内容"""
         payload = _build_payload(model, request)
-        response = self.api_client.generate_content(payload, model, api_key)
+        response = await self.api_client.generate_content(payload, model, api_key)
         return self.response_handler.handle_response(response, model, stream=False)
 
     async def stream_generate_content(self, model: str, request: GeminiRequest, api_key: str) -> AsyncGenerator[str, None]:
diff --git a/app/services/openai_chat_service.py b/app/services/openai_chat_service.py
index 5852eb2..bd8c566 100644
--- a/app/services/openai_chat_service.py
+++ b/app/services/openai_chat_service.py
@@ -144,13 +144,13 @@ class OpenAIChatService:
 
         if request.stream:
             return self._handle_stream_completion(request.model, payload, api_key)
-        return self._handle_normal_completion(request.model, payload, api_key)
+        return await self._handle_normal_completion(request.model, payload, api_key)
 
-    def _handle_normal_completion(
+    async def _handle_normal_completion(
             self, model: str, payload: Dict[str, Any], api_key: str
     ) -> Dict[str, Any]:
         """处理普通聊天完成"""
-        response = self.api_client.generate_content(payload, model, api_key)
+        response = await self.api_client.generate_content(payload, model, api_key)
         return self.response_handler.handle_response(
             response, model, stream=False, finish_reason="stop"
         )
diff --git a/docker-compose.yml b/docker-compose.yml
new file mode 100644
index 0000000..965b3fa
--- /dev/null
+++ b/docker-compose.yml
@@ -0,0 +1,9 @@
+version: '3'
+
+services:
+  gemini-balance:
+    build: .
+    ports:
+      - "8000:8000"
+    env_file:
+      - .env