Tencent Cloud one-click deployment OpenClaw tutorial (2026 version)

Compared to manually installing Node.js, setting up the environment, and deploying everything step by step, Tencent Cloud’s application image approach removes all that hassle. When you buy the server, you just pick the OpenClaw image — once it boots up, the entire environment and software are already installed and ready to go. You jump straight into the console to configure it. For beginners, this is hands-down the fastest way to get started.

1. What you need before starting

Just three things: a Tencent Cloud account, a cloud server, and an API key for your AI model.

You can prepare the API key before buying the server. I recommend OpenRouter — one key gives you access to over 400 models without signing up for each platform separately. Head to openrouter.ai, create an account, generate a key on the API Keys page, and keep it handy.

2. Purchase the server

Log into the Tencent Cloud console, go to Lighthouse Application Server, and click Create Instance.

For the region, choose Singapore, Silicon Valley, or Tokyo. These nodes give you low latency and reliable connections to overseas APIs like OpenAI, Claude, and OpenRouter, with almost no timeout risk. Domestic nodes tend to cause issues when calling overseas APIs, so they’re not ideal for this setup.

Pricing reference: 2-core 2GB usually runs around ¥30–60/month; 2-core 4GB is roughly ¥60–100/month. New users often get discounts.

Click Buy Now, complete payment, and the server usually activates in 1–2 minutes. The public IP will show up in your instance list.

3. Access the OpenClaw console

Once the server is running, OpenClaw starts automatically — no extra steps needed.

Open a browser and go to:

http://your_server_IP:18789

If the page doesn’t load, check the firewall settings in the Tencent Cloud console.

4. Open the firewall port

In the Lighthouse console, go to Firewall settings and add an inbound rule:

Protocol: TCP
Port: 18789
Source: 0.0.0.0/0

Save the rule, then refresh the console address — it should load normally.

5. Configure the AI model

In the OpenClaw backend, go to the model configuration page and fill in:

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

It’s smart to set a cost-effective entry-level model as the default — use it for routine tasks and only switch to a more powerful one when you really need it. This keeps API costs under control.

After saving, click Test Connection to make sure the API is working.

6. Connect a messaging channel

OpenClaw supports Telegram, Feishu, DingTalk, and WeCom for receiving instructions and sending notifications. Using Telegram as an example:

Search for BotFather in Telegram and send /newbot. Follow the prompts to name your bot. You’ll get a token that looks like this:

1234567890:ABCdefGHIjklMNOpqrSTUvwxYZ

Go back to the OpenClaw backend, find Telegram in the channel settings, paste the token, and save. Then find your new bot and send /start — you should get a reply confirming the connection works. From then on, you can send commands and get results directly from Telegram on your phone.

7. Confirm automatic restart

Application images are usually set to start on boot, but it’s worth double-checking. Log into the server (either through the console’s Login button or SSH) and run:

systemctl status openclaw

If you see active (running), everything is healthy and auto-start is already configured.

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

systemctl start openclaw
systemctl enable openclaw

8. Common issues

If you can’t reach the backend, check in this order: whether the firewall rule for port 18789 is open, whether the service is actually running (systemctl status openclaw), and whether you’re using the correct IP.

If the service slows down or crashes after running for a while, it’s usually because of insufficient memory. Add a swap file to relieve the pressure:

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

To update OpenClaw to the latest version:

npm update -g openclaw
systemctl restart openclaw

To view live logs for troubleshooting:

journalctl -u openclaw -f

Summary

The entire Tencent Cloud one-click deployment basically comes down to three steps: choose the OpenClaw application image when buying the server, open the firewall port, and configure the API key in the console. No command-line work is required, and you can have everything running in under five minutes. Pair it with OpenRouter’s multi-model routing and you’ve got one of the fastest and most cost-effective ways for users in China to get a 24/7 AI assistant up and running right now.

https://cloud.tencent.com/