Deploy and Host Open WebUI on Railway

Open WebUI is a self-hosted chat interface for large language models. It works with OpenAI-compatible APIs and Ollama, and adds conversation history, document upload, RAG, user accounts and role-based access.

About Hosting Open WebUI

This template runs the official ghcr.io/open-webui/open-webui:main image with a persistent volume at /app/backend/data, so accounts, chats and uploaded files survive redeploys. A secret key for sessions is generated for you, and the built-in SQLite database means no separate database service is needed. On first visit, the first account you create becomes the administrator. Then add your model provider in Admin Settings, Connections: an OpenAI-compatible API URL and key, or the address of an Ollama server.

Common Use Cases

A private ChatGPT-style interface for your team over the API of your choice
A front end for a self-hosted Ollama or other OpenAI-compatible server
Chat with your own documents using built-in retrieval

Dependencies for Open WebUI Hosting

One service with a volume; nothing else
A model provider (an API key or an Ollama server), added in the UI after deploy

Deployment Dependencies

Why Deploy Open WebUI on Railway?

Railway gives you a public HTTPS URL, a persistent volume and automatic restarts with no server to maintain. Open the URL after the deploy, create the admin account, and connect a model provider.