Skip to content

Open WebUI on a VPS

Web UI for LLMs

Author
Open WebUI Inc.
License
Open WebUI License
Version
0.11.4

The script is free · VPS from $4.63 per month · installs in about 2 minutes

Install over SSH

root@vps:~# command -v docker >/dev/null || curl -fsSL https://get.docker.com | sh; docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main

  • SystemUbuntu 24.04 · x86_64ok
  • Sourcegithub.com/open-webui/open-webuiok
  • Version0.11.4ok
  • Port3000/tcplisten

✓ Open WebUI 0.11.4 installed · about 2 minutes

root@vps:~#

Install command from the library. Output is shortened and may differ on your server.

What it is

  • AI
  • ChatGPT
  • Ollama
  • RAG

Open WebUI is a ChatGPT-style web interface for local Ollama models and any OpenAI-compatible API. Chats, history, document uploads, search across them (RAG) and multiple users.

A convenient way to give your team AI access through your own server: API keys stay with you, and you can switch models in a single window.

License: Open WebUI License, which is BSD-3-Clause with an additional branding-retention clause.

  • ChatGPT-style interface
  • Ollama and OpenAI-compatible APIs
  • Document uploads and RAG
  • Users, roles and groups
  • Web search and tools

Recommended plan

For Open WebUI: at least 2 vCPU, 3 GB RAM and 45 GB NVMe.

Minimum to run
1 vCPU · 2 GB RAM · 10 GB disk
Systems
Ubuntu 22.04 · Ubuntu 24.04 · Debian 12

How to install

Three steps in the bot or one command over SSH; installation takes about 2 minutes.

  1. 01

    Choose a plan in the bot

    Open @ExpressHost_bot and pay for a VPS. The server will be ready in about 60 seconds.

  2. 02

    Add Open WebUI

    At the “Add-ons” step pick the script from the library, or run it later: Server settings → Scripts.

  3. 03

    Open http://SERVER-IP:3000 — the first registered user becomes the administrator

    The bot will send the server address and login details to the chat.

Manually over SSH

Connect to the server as root and run the command. Supported systems: Ubuntu 22.04, Ubuntu 24.04, Debian 12.

Install command
command -v docker >/dev/null || curl -fsSL https://get.docker.com | sh; docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main

Ports

Open WebUI ports
PortProtocolPurpose
3000tcpWeb interface

After installation

  1. 1.Open http://SERVER-IP:3000 — the first registered user becomes the administrator
  2. 2.In the settings, connect Ollama on this server (address http://host.docker.internal:11434) or an OpenAI-compatible API key
  3. 3.Disable open registration in the Admin Panel if the service is not meant for everyone

Open WebUI FAQ

Didn’t find an answer? Message @ExpressHost_SupportBot.

Do I need Ollama?

No. Open WebUI also works with external APIs (OpenAI, OpenRouter and others). Ollama is needed for models on your own server; in that case choose a plan with at least 8 GB RAM.

How do I update?

Run docker pull ghcr.io/open-webui/open-webui:main and recreate the container with the same command.

Where are chats and settings stored?

In the open-webui Docker volume (folder /app/backend/data).

Open WebUI installs at checkout — in the bot.