Deploy and Host LiteLLM (w/ Open WebUI) on Railway

LiteLLM puts one OpenAI-compatible API in front of 100+ LLM providers; Open WebUI adds a ChatGPT-style chat for your team. Every chat goes through LiteLLM, so you see each person's spend.

About Hosting LiteLLM (w/ Open WebUI)

Deploy with your email and a password. Setup connects Open WebUI to LiteLLM.
Sign in to LiteLLM at /ui with them and add a model with your provider key.
Sign in to Open WebUI and chat. Add your team in Admin Panel.

Common Use Cases

Private ChatGPT for your team
Spend tracking per person
One gateway for chat and apps

Dependencies for LiteLLM (w/ Open WebUI) Hosting

PostgreSQL
Open WebUI

Deployment Dependencies

Implementation Details

Architecture: Open WebUI sends each person's chats to LiteLLM; apps call LiteLLM directly; Postgres and Setup stay private

Needs about 1.2 GB (Trial or a paid plan). Attached documents go to the model in full. Back up Postgres and the Open WebUI volume; never change LITELLM_SALT_KEY. For a custom domain, add it to CORS_ALLOW_ORIGIN.

Why Deploy LiteLLM (w/ Open WebUI) 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 LiteLLM (w/ Open WebUI) on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.

Updated 2026-10-28: first release, LiteLLM 1.106.6 and Open WebUI 0.12.