Simple, transparent pricing
Choose the plan that fits your needs. All plans include Hetzner hosting management. Server costs are separate and billed directly by Hetzner.
Base
For individuals getting started with their personal AI assistant.
- Up to 3 bot instances
- All messaging platforms
- Unlimited messages
- Automated backups
- Basic analytics
- Email support
Pro
For power users who need more control and customization.
- Unlimited bot instances
- All messaging platforms
- Unlimited messages
- Automated backups
- Advanced analytics
- Priority support
- Custom domain
- API access
Agency
For teams and agencies managing multiple AI deployments.
- Everything in Pro
- Up to 10 team seats
- Whitelabel dashboard
- Bot templates
- Audit logs
- Dedicated support
Hetzner Server Tiers
In addition to your plan, you pay Hetzner directly for your cloud server. Check Hetzner's website for current pricing.
Light usage, 1-2 platforms
Recommended for most users
Heavy usage, local AI models
What You'll Need
Two things to get started alongside your OpenClaw Hetzner plan.
AI Provider API Key
Bring your own API key from Anthropic (Claude), OpenAI (GPT), or run local models with Ollama on your server.
Hetzner Account
Create a free Hetzner Cloud account and generate an API token. We handle the rest — provisioning, configuration, and deployment.
Frequently Asked Questions
Have more questions? Get in touch.
What is OpenClaw?
OpenClaw is an open-source personal AI assistant created by Peter Steinberger. It runs on your own hardware, integrates with WhatsApp, Telegram, Discord, Slack, Signal, and iMessage, and features persistent memory, browser control, file management, and shell access. Think of it as a personal OS that lives in your chat apps.
Why Hetzner specifically?
Hetzner offers excellent price-performance in European cloud hosting, with significantly more compute per dollar compared to equivalent AWS or GCP instances. Their data centers in Germany and Finland ensure GDPR compliance and low latency for European users. Check Hetzner's website for current server pricing.
What server specs do I need?
For most users, we recommend the Hetzner CX32 (4 vCPU, 8 GB RAM, 80 GB SSD). If you plan to run local AI models or connect many platforms simultaneously, consider the CX42 (8 vCPU, 16 GB RAM). Check Hetzner's website for current pricing.
Do I need my own AI API key?
Yes. OpenClaw supports Claude (Anthropic), GPT (OpenAI), and local models via Ollama. You bring your own API key for cloud models, or run local models entirely on your Hetzner server for complete privacy.
How does deployment work?
After signing up, you provide your Hetzner API token. Our system provisions a server, installs OpenClaw, configures your chosen messaging platforms, and hands you the keys. The entire process takes under 5 minutes.
Is my data secure?
Your data never leaves your Hetzner server. OpenClaw runs entirely on your infrastructure. We have zero access to your conversations, files, or AI interactions. Hetzner data centers are ISO 27001 certified with physical security, redundant power, and encrypted storage.
Can I run local AI models?
Yes. OpenClaw supports Ollama for running local LLMs. With a Hetzner CX42 or dedicated server, you can run models like Llama, Mistral, or Phi entirely on your server with no data leaving your infrastructure.
What messaging platforms are supported?
OpenClaw supports WhatsApp, Telegram, Discord, Slack, Signal, and iMessage. Microsoft Teams and Matrix support is coming soon. Your assistant maintains persistent memory across all connected platforms.