---
title: "Deploy nimbus-llm-proxy"
description: "LLM proxy with Redis that forwards requests to an upstream API"
category: "AI/ML"
url: https://railway.com/deploy/nimbus-llm-proxy
---

# Deploy nimbus-llm-proxy

LLM proxy with Redis that forwards requests to an upstream API

**[Deploy nimbus-llm-proxy on Railway](https://railway.com/template/nimbus-llm-proxy)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/nimbus-llm-proxy/manifest.json

- **Creator:** Sunday Johnson's Projects
- **Category:** AI/ML
- **Total deploys:** 1

## Template content

### llm-proxy

- **Image:** ghcr.io/yoodule/nimbus/llm-proxy:v1.2.0
- **Public domain:** Yes

### Redis https://cdn.sanity.io/images/sy1jschh/production/0ce0bfdcfbdbf69662b1116671f97c2dd788b655-157x157.svg

- **Image:** redis:8.2
- **Start command:** `/bin/sh -c "rm -rf $RAILWAY_VOLUME_MOUNT_PATH/lost+found/ && exec docker-entrypoint.sh redis-server --requirepass $REDIS_PASSWORD --save 60 1 --dir $RAILWAY_VOLUME_MOUNT_PATH"`

## Documentation

# Deploy and Host nimbus-llm-proxy on Railway

nimbus-llm-proxy is an LLM proxy that sits between your apps and an upstream LLM API. Your apps call the proxy, and it forwards requests to the upstream provider using the API keys you configure, so those keys stay on the server instead of in your clients.

## About Hosting nimbus-llm-proxy

This template deploys two services on Railway: the nimbus-llm-proxy service and a Redis database. The proxy connects to Redis over Railway's private network, and the Redis connection variables are linked for you. On deploy, Railway generates the Redis password and the proxy secret. You only need to enter the upstream base URL and your upstream API key or keys. Once the deploy finishes, point your apps at the proxy's public URL.

## Common Use Cases

- Keep upstream API keys out of client apps and browsers
- Route several apps through a single LLM endpoint
- Swap or change the upstream provider without updating every client
- Share one set of upstream keys across a team

## Dependencies for nimbus-llm-proxy Hosting

- Redis, included in this template
- An upstream LLM API and a valid API key for it

### Implementation Details

Set `UPSTREAM_BASE` to the base URL of the provider you want to forward to, and `UPSTREAM_API_KEYS` to your key or keys for that provider. `NIMBUS_PROXY_SECRET` is generated on first deploy. Copy it from the service's Variables tab and keep it private. Never put real API keys in a public template or commit them to a repository.

## Why Deploy nimbus-llm-proxy 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 nimbus-llm-proxy 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.

## 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/nimbus-llm-proxy