---
title: "Deploy Open WebUI | Self-Hosted LLM Chat with a Real Volume"
description: "Self-hosted chat UI for LLMs, on a pinned release with a persistent volume"
category: "AI/ML"
url: https://railway.com/deploy/open-webui-or-self-hosted-llm-chat-with-
---

# Deploy Open WebUI | Self-Hosted LLM Chat with a Real Volume

Self-hosted chat UI for LLMs, on a pinned release with a persistent volume

**[Deploy Open WebUI | Self-Hosted LLM Chat with a Real Volume on Railway](https://railway.com/template/open-webui-or-self-hosted-llm-chat-with-)**

- **Creator:** Pavel Volkov's Projects
- **Category:** AI/ML
- **Total deploys:** 1

## Template content

### Open WebUI

- **Image:** ghcr.io/open-webui/open-webui:0.10.2
- **Public domain:** Yes

## Documentation

# Deploy and Host Open WebUI on Railway

Open WebUI is a self-hosted web interface for large language models. It talks to Ollama or any OpenAI-compatible endpoint, keeps chats, users and settings in its own database, and runs entirely on infrastructure you control.

## About Hosting Open WebUI

This template runs the official image on a pinned release, 0.10.2, rather than a floating tag, so a redeploy gives you back the same version you verified. The container listens on 8080 and is served over HTTPS on a Railway domain.

State lives on a persistent volume mounted at /app/backend/data: the database, uploaded files and the vector index survive restarts and redeploys. WEBUI_SECRET_KEY is generated per deployment, so sessions are not signed with an empty or shared key.

## Common Use Cases

- A private ChatGPT-style front end for a team, pointed at your own Ollama server or an OpenAI-compatible API
- A shared workspace for prompts, documents and retrieval over uploaded files
- One vendor-neutral UI in front of several model providers at once

## Dependencies for Open WebUI Hosting

- A persistent volume, included in this template, for the database and uploads
- A model backend: an Ollama instance, or any OpenAI-compatible endpoint. Point it at one after the first deploy under Settings, or add OLLAMA_BASE_URL / OPENAI_API_BASE_URL as service variables.

### Deployment Dependencies

- Open WebUI documentation: https://docs.openwebui.com
- Source: https://github.com/open-webui/open-webui

### Implementation Details

Variables the template sets for you:

| Variable | Value | Why |
|---|---|---|
| PORT | 8080 | The port the image actually listens on |
| DATA_DIR | /app/backend/data | Points the app at the mounted volume |
| WEBUI_URL | the public domain | Correct absolute links and OAuth redirects |
| WEBUI_SECRET_KEY | generated | Signs sessions, unique per deployment |
| ENABLE_SIGNUP | true | Lets you create the first account |

The first account you create becomes the administrator. Set ENABLE_SIGNUP to false afterwards to close registration.

## Why Deploy Open WebUI on Railway?

Railway gives it exactly what it needs: a volume that persists, HTTPS on a domain without extra setup, and a redeploy that keeps your data. When a new release lands, change the image tag and redeploy.

## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage.
- [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

Open this page in a browser: https://railway.com/deploy/open-webui-or-self-hosted-llm-chat-with-