Deploy and Host LiteLLM (w/ spend tracking) on Railway

LiteLLM puts one OpenAI-compatible API in front of 100+ LLM providers. This template saves virtual keys, budgets and spend in Postgres, and you sign in with the password you choose on the deploy form.

About Hosting LiteLLM (w/ spend tracking)

You get LiteLLM 1.106.6 and a private Postgres, with the master key and encryption key generated per deploy. Open your LiteLLM URL at /ui and sign in as admin. Add a model with your provider key, then create a virtual key for each app.

Common Use Cases

One endpoint for coding agents
Per-team keys with budgets
Spend tracking across providers

Dependencies for LiteLLM (w/ spend tracking) Hosting

PostgreSQL

Deployment Dependencies

Implementation Details

Architecture: apps and your team reach LiteLLM; Postgres stays on the private network; LiteLLM calls your LLM providers

Needs about 0.9 GB, so use Trial or a paid plan; the Free plan can't run LiteLLM. Back up Postgres, and never change LITELLM_SALT_KEY: it encrypts the provider keys saved there.

Why Deploy LiteLLM (w/ spend tracking) 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/ spend tracking) 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.