---
title: "Deploy Open WebUI + Bifrost | Self-Hosted ChatGPT for Every LLM"
description: "Deploy and Host Open WebUI + Bifrost"
category: "AI/ML"
url: https://railway.com/deploy/open-webui-bifrost-or-self-hosted-chatgp
---

# Deploy Open WebUI + Bifrost | Self-Hosted ChatGPT for Every LLM

Deploy and Host Open WebUI + Bifrost

**[Deploy Open WebUI + Bifrost | Self-Hosted ChatGPT for Every LLM on Railway](https://railway.com/template/open-webui-bifrost-or-self-hosted-chatgp)**

- **Creator:** Maxim AI's Projects
- **Category:** AI/ML
- **Total deploys:** 5

## Template content

### Postgres https://upload.wikimedia.org/wikipedia/commons/2/29/Postgresql_elephant.svg

- **Image:** ghcr.io/railwayapp-templates/postgres-ssl:18

### Open WebUI https://docs.openwebui.com/assets/files/open-webui-logo-transparent-9665c5e6fe8abe6bfab2ba83db0c409a.png

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

### Bifrost https://framerusercontent.com/images/k49dViw06yckDjJt5uERdfTSjU.png

- **Image:** maximhq/bifrost:latest
- **Health check:** /health
- **Public domain:** Yes

## Documentation

# Deploy and Host Open WebUI + Bifrost on Railway

A private, self-hosted ChatGPT alternative connected to every major LLM provider. Powered by Open WebUI, Bifrost, and Postgres — fully yours, zero vendor lock-in, one-click deploy. Open WebUI gives you the polished chat interface; Bifrost is the high-performance AI gateway that routes to 20+ providers (OpenAI, Anthropic, Google, AWS Bedrock, and more) with automatic failover, semantic caching, virtual keys, and cost tracking built in.

## About Hosting Open WebUI + Bifrost

This template deploys a complete private AI workspace across three services: Open WebUI as the chat frontend, Bifrost as the multi-provider AI gateway, and Postgres for persistent storage. All services are pre-wired through Railway's internal private network with auto-generated secrets — no manual networking required.

After deploy, open the Bifrost dashboard to add your API keys (OpenAI, Anthropic, Groq, Gemini, or any supported provider), then open Open WebUI and start chatting. The first account created automatically becomes admin. Every message routes through Bifrost, so you get failover, caching, per-user budgets, and full request logging out of the box.

## Common Use Cases

- Private ChatGPT alternative — chat over OpenAI, Anthropic, Gemini, Bedrock, and more without conversations being logged by a third-party UI
- Team LLM gateway — shared, access-controlled chat with per-user budgets, rate limits, and request logging through Bifrost's governance layer
- Cost-optimized AI — semantic caching serves repeated queries instantly and cuts token spend

## Dependencies for Open WebUI + Bifrost Hosting

- PostgreSQL 16+ for Bifrost config and request log storage

### Deployment Dependencies

- Open WebUI: https://github.com/open-webui/open-webui
- Bifrost Docs: https://docs.getbifrost.ai
- Bifrost Docker Hub: https://hub.docker.com/r/maximhq/bifrost

### Why Deploy Open WebUI + Bifrost on Railway?

Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying Open WebUI + Bifrost on Railway, you get a complete private AI chat platform connected to every major model provider in minutes — with cost governance and observability built in.

## 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-bifrost-or-self-hosted-chatgp