Why Host Open WebUI on a VPS?
Self-hosting Open WebUI on a VPS lets you keep full control over your conversations, your models and your data — no third party can access them. You get permanent availability, reachable from any browser, with no usage limit imposed by a public cloud plan. It is the ideal solution for developers, teams and businesses that want to harness the power of LLMs in full sovereignty.
What You Can Do With Open WebUI
- Chat with local models via Ollama (Mistral, LLaMA 3, Gemma, etc.) or with the OpenAI API
- Manage several models and switch between them in one click from a unified interface
- Create and share custom assistants with tailored system instructions
- Upload and analyse documents (PDF, text) directly in the chat thanks to built-in RAG support
- Open access to your team with a system of user accounts and roles
- Review the full history of your conversations, stored on your own server
Install Open WebUI on Your ServOrbit VPS
Order a ServOrbit Cloud VPS
Go to /vps-cloud and choose a plan suited to your usage. For Open WebUI paired with Ollama, a VPS with at least 4 GB of RAM and 2 vCPU is recommended. Complete the order: your server is provisioned in under 60 seconds.
Access the Marketplace from the client area
Log in to your ServOrbit client area, then navigate to the Marketplace section in your VPS management panel. There you will find a selection of applications ready to deploy in one click.
Select Open WebUI and start the installation
Search for Open WebUI in the Marketplace list, click the application's card, then confirm the installation. The system automatically deploys Open WebUI via Docker on your VPS — no command to type.
Create your administrator account
Once the installation is complete, open Open WebUI in your browser at http://YOUR_IP:3000. On first connection, Open WebUI prompts you to create an administrator account: enter a name, an email address and a password. This first account automatically gets administration rights.
Connect a model and get started
From the administration settings (icon at the top right), configure the connection to your Ollama instance (http://localhost:11434 if Ollama is installed on the same VPS) or enter your OpenAI API key. Then select a model from the list and start chatting immediately.
To secure your Open WebUI instance from the start, place it behind an Nginx reverse proxy with a Let's Encrypt TLS certificate and point a dedicated subdomain (e.g. ai.yourdomain.com) to your VPS. That way, all your communications are encrypted and you can share access with your team without exposing a raw port to the Internet.
The Official Documentation
For advanced configuration, tool-specific options and version changes, refer to the official Open WebUI documentation. This guide covers going live on a ServOrbit VPS; the vendor's documentation remains the reference for fine-tuning.
