No need to buy a Mac Mini! Run OpenClaw 24/7 at a low cost of $6/month with Hostinger VPS

I used to think running OpenClaw long-term meant committing to dedicated hardware—either buying a Mac Mini to keep at home or renting an expensive cloud server. It turns out neither is necessary. With Hostinger VPS, the whole setup comes in at around $6 a month.

You only need two things: a Hostinger VPS and an OpenRouter API key.

Why Hostinger VPS

The foundation of this setup is Hostinger's KVM2 plan: 2-core CPU, 8GB RAM, 100GB NVMe SSD, at roughly $6/month on a two-year term.

The 8GB of RAM is what matters most. It gives an AI agent enough headroom to run without frequent crashes. The NVMe storage means noticeably faster read/write speeds compared to standard SSDs—you'll feel the difference in deployment and startup times. Hostinger also supports Alipay, which removes the payment barrier for users in China.

Running locally has real drawbacks: the agent goes offline when your computer shuts down, your IP is unstable, and remote management is a hassle. A VPS solves all of that—24/7 uptime, a dedicated public IP, and the ability to send commands from your phone via Telegram without ever opening a laptop.

Why OpenRouter

One OpenRouter API key gives you access to over 400 models—Minimax, Claude, GPT, and more—with intelligent switching based on task type. The cost-saving logic is simple: use cheap models for routine tasks and reserve top-tier models for complex reasoning. Monthly model costs can stay in the single digits, which is more than 20 times cheaper than a standalone Claude Opus subscription.

Full Deployment Walkthrough

Step 1: Purchase Hostinger KVM2 VPS

Go to the Hostinger website, navigate to VPS Hosting, and select the KVM2 plan.

Configuration options:

• Operating system: Ubuntu 22.04
• Plan: KVM2 (2 cores, 8GB RAM)
• Data center: choose a node close to your target users—Europe for European users, Singapore or the US for Asia-Pacific

After purchase, Hostinger will email you the server IP and initial root password. You can also find these directly in the hPanel console.

Step 2: Connect via SSH

Open a terminal (Mac/Linux can use the system terminal directly; Windows users can use PowerShell or PuTTY):

ssh root@your_server_IP

Enter the initial password, then update the system on first login:

apt update && apt upgrade -y

For security, create a regular user instead of operating as root long-term:

adduser yourname
usermod -aG sudo yourname
su - yourname

Step 3: Install Docker

Hostinger's Ubuntu 22.04 image doesn't include Docker by default, so install it manually:

sudo apt install -y ca-certificates curl gnupg
sudo install -m 0755 -d /etc/apt/keyrings
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg
sudo chmod a+r /etc/apt/keyrings/docker.gpg

echo \
  "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] \
  https://download.docker.com/linux/ubuntu \
  $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
  sudo tee /etc/apt/sources.list.d/docker.list > /dev/null

sudo apt update
sudo apt install -y docker-ce docker-ce-cli containerd.io docker-compose-plugin

Verify the installation:

sudo docker --version

Add your user to the Docker group to avoid typing sudo every time:

sudo usermod -aG docker $USER
newgrp docker

Step 4: Deploy OpenClaw

Pull the image and start the container:

docker pull openclaw/openclaw:latest

docker run -d \
  --name openclaw \
  --restart always \
  -p 8080:8080 \
  -v ~/.openclaw:/app/data \
  openclaw/openclaw:latest

A quick note on the parameters:

• --restart always: the container starts automatically after any VPS reboot—no manual intervention needed
• -p 8080:8080: maps the container's port 8080 to the host
• -v ~/.openclaw:/app/data: mounts data locally so nothing is lost if the container is removed

Confirm the container is running:

docker ps

If you see openclaw with a status of Up, deployment was successful.

Step 5: Configure the Hostinger Firewall

Hostinger's hPanel includes a built-in firewall. Go to the console, find Firewall settings, and add a rule to open port 8080.

Alternatively, configure it directly on the server with ufw:

sudo ufw allow 8080
sudo ufw allow ssh
sudo ufw enable

Step 6: Configure OpenRouter

Go to openrouter.ai, create an account, navigate to API Keys, and generate a new key.

In your browser, open:

http://your_server_IP:8080

Go to OpenClaw's settings and fill in:

• API Base URL: https://openrouter.ai/api/v1
• API Key: the key you just generated
• Default model: minimax/minimax-01 (an affordable entry-level model that handles most tasks well)

Save and click Test Connection to confirm the API is working.

Step 7: Set Up Model Routing

In OpenClaw's CloudOps settings, assign models by task type:

Main Agent (daily tasks)      → minimax/minimax-01
Sub-Agent (data processing)   → deepseek/deepseek-chat
Complex reasoning tasks       → anthropic/claude-3-5-sonnet
Fallback                      → openai/gpt-4o-mini

The cheap models handle the bulk of the work; the top-tier model only gets called when it's genuinely needed. This keeps monthly model costs very low.

Step 8: Connect Telegram

Search for BotFather in Telegram and send /newbot. Follow the prompts to name your bot. You'll receive a token in this format:

1234567890:ABCdefGHIjklMNOpqrSTUvwxYZ

Copy the token, paste it into the Telegram Bot Token field in OpenClaw's settings, and save. Find your new bot and send /start—if you get a reply, the connection is working. From here on, you can send instructions to your AI directly from Telegram on your phone, no backend login required.

Step 9: Automate Configuration Backups

Over time, your agent will accumulate memory data. Since Hostinger VPS occasionally restarts for maintenance, it's worth syncing your configuration to a private GitHub repository automatically.

Create a private repo on GitHub and generate a Personal Access Token (Settings → Developer settings → Personal access tokens → Generate new token).

Configure Git on the server:

git config --global user.email "[email protected]"
git config --global user.name "yourname"

Create a sync script:

nano ~/.openclaw/sync.sh

Add the following:

#!/bin/bash
cd ~/.openclaw
git init
git remote add origin https://yourname:[email protected]/yourname/openclaw-backup.git 2>/dev/null || true
git add .
git commit -m "sync $(date '+%Y-%m-%d %H:%M:%S')"
git push -u origin main 2>/dev/null || git push origin main

Make it executable:

chmod +x ~/.openclaw/sync.sh

Set up a cron job to sync every 10 minutes:

crontab -e

Add this line at the end:

*/10 * * * * ~/.openclaw/sync.sh >> ~/.openclaw/sync.log 2>&1

Save and exit—backups are now running automatically.

Cost Comparison

For most people, total monthly costs stay well under $10.

Day-to-Day Maintenance Commands

Once everything is set up, you'll rarely need to touch it. Here are the commands worth keeping handy:

Restart the container:

docker restart openclaw

View live logs:

docker logs -f openclaw

Check memory usage:

docker stats openclaw

Update to the latest version:

docker pull openclaw/openclaw:latest
docker stop openclaw
docker rm openclaw
docker run -d --name openclaw --restart always -p 8080:8080 -v ~/.openclaw:/app/data openclaw/openclaw:latest

Who This Is For

This setup works for anyone who wants an AI running around the clock—whether for automated tasks, content generation, customer workflows, or simply turning OpenClaw into a reliable long-term tool. The Hostinger KVM2 configuration handles it all comfortably, the price is competitive among comparable providers, and Alipay support makes it accessible for users in China. For anyone looking to run OpenClaw sustainably, this is currently one of the most cost-effective ways to do it.