Ollama
Run LLMs locally
AI / AutomationFree
Web UI for LLMs
The script is free · VPS from $4.63 per month · installs in about 2 minutes
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
✓ Open WebUI 0.11.4 installed · about 2 minutes
root@vps:~#
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.
For Open WebUI: at least 2 vCPU, 3 GB RAM and 45 GB NVMe.
Three steps in the bot or one command over SSH; installation takes about 2 minutes.
Open @ExpressHost_bot and pay for a VPS. The server will be ready in about 60 seconds.
At the “Add-ons” step pick the script from the library, or run it later: Server settings → Scripts.
http://SERVER-IP:3000 — the first registered user becomes the administratorThe bot will send the server address and login details to the chat.
Connect to the server as root and run the command. Supported systems: Ubuntu 22.04, Ubuntu 24.04, Debian 12.
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| Port | Protocol | Purpose |
|---|---|---|
| 3000 | tcp | Web interface |
http://SERVER-IP:3000 — the first registered user becomes the administratorhttp://host.docker.internal:11434) or an OpenAI-compatible API keyDidn’t find an answer? Message @ExpressHost_SupportBot.
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.
Run docker pull ghcr.io/open-webui/open-webui:main and recreate the container with the same command.
In the open-webui Docker volume (folder /app/backend/data).
Open WebUI installs at checkout — in the bot.
Netherlands, Amsterdam
$5.16/mo
$0.18 for 24 hours · $1.29 for 7 days
Pick Open WebUI at the “Scripts” step when you order the server.
Germany, Frankfurt
$6.50/mo
$0.23 for 24 hours · $1.63 for 7 days
Pick Open WebUI at the “Scripts” step when you order the server.
Poland, Warsaw
$4.63/mo
$0.17 for 24 hours · $1.16 for 7 days
Pick Open WebUI at the “Scripts” step when you order the server.
Estonia, Tallinn
$5.83/mo
$0.21 for 24 hours · $1.46 for 7 days
Pick Open WebUI at the “Scripts” step when you order the server.