希望通过设置一个nginx反向代理，来代理阿里云千问大模型的api接口

本地测试，通过配置nginx.conf文件，实现访问指定ip+端口能够自动转发至千问的API，但实际情况通过阅读nginx日志，请求被强制转发至https的协议，实际期望是使用http。想请问如何解决nginx代理转发的问题。

``` server {
listen 8162;
server_name localhost;

    location /compatible-mode/v1/chat/completions {
        proxy_pass http://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions;  
        proxy_set_header Host $host;  
        proxy_set_header X-Real-IP $remote_addr;  
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; 
        proxy_set_header X-Forwarded-Proto $scheme;  

        proxy_set_header Authorization "Bearer **";
        proxy_set_header Content-Type "application/json";

    }

当访问localhost:8162/compatible-mode/v1/chat/completions地址时，期望被转发到千问模型的API。但实际返回结果报错
```{
    "error": {
        "message": "You didn't provide an API key. You need to provide your API key in an Authorization header using Bearer auth (i.e. Authorization: Bearer YOUR_KEY). ",
        "type": "invalid_request_error",
        "param": null,
        "code": null
    },
    "request_id": "dffc652a-ac69-9d18-9a64-037c20a18a8c"
}

nginx日志可以看到被永久重定向到https地址

```2025/01/22 14:53:49 [debug] 22244#24384: *1 HTTP/1.1 308 Permanent Redirect
Server: nginx/1.24.0
Date: Wed, 22 Jan 2025 06:53:49 GMT
Content-Length: 0
Connection: keep-alive
location: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
vary: Accept-Encoding

```

但本地使用postman直接调用http的阿里云地址是正常的。
想请问如何使用nginx来代理阿里云的大模型API。