Alibaba Cloud one-click deployment of OpenClaw complete tutorial (2026 latest version)

Manual deployment means installing Node.js, configuring the environment, and working through dependency issues—a non-trivial barrier for newcomers. Alibaba Cloud's application image approach skips all of that: select the OpenClaw image when purchasing the server, and by the time the system boots, the program is already running. You go straight to the console for configuration.

1. Purchase the server

Log into the Alibaba Cloud console, navigate to Lightweight Application Server, and click Create Instance.

Choose Singapore, Hong Kong, or a US node for the region. These locations provide stable connectivity when calling overseas APIs like OpenAI, Claude, and Tongyi Qianwen. Domestic nodes tend to time out when accessing overseas services and aren't recommended for this use case.

Use at least 2GB of RAM. OpenClaw's memory usage climbs when browser automation tasks are running, and 1GB will struggle. Complete payment after confirming your configuration—the server typically activates within 1–2 minutes.

2. Service starts automatically

With an OpenClaw application image, the server handles everything on boot: installing the runtime environment, deploying the OpenClaw program, and starting the background service. No SSH login or command-line work required. Once the server status shows "Running," wait about a minute for the service to fully initialize.

3. Open the access port

In the Alibaba Cloud Lightweight Server console, go to the instance details page and open Firewall settings.

OpenClaw uses a dynamic port rather than a fixed one. Look for an Application Details or Port Allow option in the console and click Execute—the system will open the correct port automatically.

If you need to add the rule manually, log into the server to find the actual port:

ssh root@your_server_IP
openclaw status
# Or check the listening port directly
ss -tlnp | grep openclaw

Note the port number and add a firewall rule:

Protocol: TCP
Port: actual port number
Source: 0.0.0.0/0

4. Get the console access address

Find the Access Control or View WebUI Address entry in the server console. Clicking it displays the access address in the format:

http://server_public_IP:port_number

Open this address in a browser to reach the OpenClaw management interface.

5. Configure the AI model

OpenClaw deployed via Alibaba Cloud connects to Tongyi Qianwen by default, but supports other models as well.

To configure Tongyi Qianwen (Model Studio), go to the Alibaba Cloud Model Studio console and create an API key. In the OpenClaw backend, fill in:

API Base URL: https://dashscope.aliyuncs.com/compatible-mode/v1
API Key: your Model Studio key
Default model: qwen-turbo (daily tasks) / qwen-max (complex tasks)

Alibaba Cloud offers token-based billing and Coding Plan packages. If your usage is relatively stable, a Coding Plan makes cost management straightforward; if usage fluctuates, pay-as-you-go is more flexible.

To access other models like Claude, GPT, or DeepSeek, OpenRouter is the more convenient option:

API Base URL: https://openrouter.ai/api/v1
API Key: your OpenRouter key
Default model: minimax/minimax-01 (low-cost entry)

Using a cheaper model for routine tasks and switching to a more capable one only when needed keeps API costs significantly lower.

6. Connect a messaging channel

Using Telegram as an example: search for BotFather, send /newbot, follow the prompts to name your bot, and receive a token:

1234567890:ABCdefGHIjklMNOpqrSTUvwxYZ

In the OpenClaw backend under channel configuration, select Telegram, paste the token, and save. Find your new bot and send /start—a reply confirms the setup is working. WeCom and DingTalk are configured from the same channel page; follow the respective platform instructions to fill in the required parameters.

7. Security configuration (do this now)

OpenClaw has elevated system permissions—it can access files, execute commands, and call APIs. Complete these steps immediately after deployment.

Configure the firewall to open only necessary ports:

ufw allow ssh
ufw allow 80/tcp
ufw allow 443/tcp
ufw enable

Add authentication via Nginx to prevent open access to the backend:

apt install nginx apache2-utils -y
htpasswd -c /etc/nginx/.htpasswd your_username

Nginx configuration:

server {
    listen 80;
    server_name your_server_IP;

    location / {
        auth_basic "Restricted Access";
        auth_basic_user_file /etc/nginx/.htpasswd;
        proxy_pass http://localhost:openclaw_port;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
    }
}

systemctl restart nginx

If you have a domain name, enable HTTPS:

apt install certbot python3-certbot-nginx -y
certbot --nginx -d your_domain

8. Common issues

If the console won't open, check in this order: whether the firewall has the correct port open, whether the service is running, and whether the IP address is correct.

Check service status:

systemctl status openclaw

If the service isn't running, start and enable it:

systemctl start openclaw
systemctl enable openclaw

If the service crashes due to insufficient memory, add a swap file:

fallocate -l 2G /swapfile
chmod 600 /swapfile
mkswap /swapfile
swapon /swapfile
echo '/swapfile none swap sw 0 0' >> /etc/fstab

View live logs for troubleshooting:

journalctl -u openclaw -f

Summary

The Alibaba Cloud one-click deployment process is four steps: select the OpenClaw image and create the server, open the access port, configure the AI model in the console, and set up a messaging channel. No complex operations required—basic deployment takes under five minutes. Complete the security configuration and you have a stable, 24-hour AI assistant ready to go.

https://www.aliyun.com