Install OpenClaw on Cloud Server with Discounted Price - Free and Best Options

Install OpenClaw on Cloud Server with Discounted Price - Free and Best Options

You want your own AI assistant but don’t want to break the bank. OpenClaw lets you self-host a powerful AI gateway on any cheap VPS. Here are two paths to get started - one costs nothing, the other gives you the best experience for just 7 EUR/month.

Two Options to Choose From

• Free (Zero Tokens) -> Use OpenClaw with OpenRouter’s free models. Register at openrouter.ai, grab a free key, and pick any :free model. No subscriptions, no credit card needed. Perfect for trying things out.
• Best (7 EUR/month) -> Get an OpenAI ChatGPT subscription and connect it via OAuth. This gives you access to top-tier models with the smoothest experience. The best bang for your buck.

Get a Cheap Server

A cloud server with 4 CPU, 6 GB RAM, and 120 GB SSD is the best option you can find. Install Ubuntu or Debian and you’re ready.

Get a discounted cloud server at dcxv.com/data-center#cloud and use promo code openclaw for 5% off your order!

5-Minute Installation

Installation is one command:

curl -fsSL https://openclaw.ai/install.sh | bash

The installer will ask onboarding questions. Select Yes when asked to continue, and choose QuickStart as the onboarding mode:

*  I understand this is personal-by-default and shared/multi-user use requires lock-down. Continue?
|  Yes
|
*  Onboarding mode
|  QuickStart

The installer will also ask you to pick an AI provider. If you want the free option, select OpenRouter - just register at openrouter.ai and create your free API key. Then pick any of the :free models from the list. For the best option, choose OpenAI and connect your ChatGPT subscription via OAuth.

It will also ask you to select a channel. Pick Telegram - you’ll need a bot token. To get one, open Telegram, chat with @BotFather (make sure the handle is exactly @BotFather), run /newbot, follow the prompts and copy the token. Paste it when the installer asks.

After the install, verify everything is working:

openclaw doctor         # check for config issues
openclaw status         # gateway status
openclaw dashboard      # open the browser UI

Start the Gateway

Step 1 - Start the gateway:

openclaw gateway --port 18789
# debug/trace mirrored to stdio
openclaw gateway --port 18789 --verbose
# force-kill listener on selected port, then start
openclaw gateway --force

Step 2 - Verify service health:

openclaw gateway status
openclaw status
openclaw logs --follow

Healthy baseline: Runtime: running and RPC probe: ok.

Step 3 - Validate channel readiness:

openclaw channels status --probe

Connect Telegram

Once the gateway is running, approve your first DM:

openclaw pairing list telegram
openclaw pairing approve telegram <CODE>

Pairing codes expire after 1 hour.

To use the bot in a group, add it to your group and configure channels.telegram.groups and groupPolicy to match your access model.

Troubleshooting

If something doesn’t work, check the official troubleshooting guide: https://docs.openclaw.ai/install#path-diagnosis-and-fix

Bottom Line

You can have your own AI assistant running in under 5 minutes on a cheap server. Go free to start, upgrade to the 7 EUR/month OpenAI option when you’re ready for the best experience. That’s it - next time we’ll cover how to configure and use it.