LiteLLM

Development1024MB+ RAM

LLM API proxy - unified interface to 100+ LLM providers

Download Server Compass Install LiteLLM to server

aillmproxyapi-gatewayopenai-compatible

Deploy LiteLLM in 3 Steps

Connect Your VPS

Add your server credentials to Server Compass

Select LiteLLM

Choose from our template library

Deploy & Configure

Fill in settings and click Deploy

No Docker knowledge required

Step-by-step deployment guide

Deploy LiteLLM on a VPS with Server Compass

Use the LiteLLM template in Server Compass to deploy a web-based LLM gateway and proxy admin service on your VPS, then verify the admin UI in a browser.

About 10 minutesBrowser verified

Step 1

Open the server Apps tab

Select the tutorial-vps VPS, open the Apps tab, and start a new app deployment. Keep sensitive server details hidden before capturing or sharing screenshots.

Server Compass Apps tab before creating a LiteLLM app

Step 2

Choose an app template

Click New App and choose the template deployment path so Server Compass can load the built-in catalog.

Choosing to deploy an app from a Server Compass template

Step 3

Search for LiteLLM

Use the template picker search to find LiteLLM in the Server Compass template catalog.

Searching for LiteLLM in the Server Compass template picker

Step 4

Select the LiteLLM template

Choose the LiteLLM template. Server Compass fills the LiteLLM service, PostgreSQL database, generated master key, generated database password, and admin port.

LiteLLM template selected in Server Compass

Step 5

Review the LiteLLM settings

Confirm the app name and compose services. In this run, the app was named litellm-demo and used host port 4000.

Reviewing LiteLLM project settings and compose services

Step 6

Deploy LiteLLM

Review the generated compose settings, confirm the web port is available, and click Deploy Now.

Reviewing LiteLLM environment variables and port before deployment

Step 7

Watch the deployment progress

Keep the deployment modal open while Server Compass uploads the compose file, pulls the LiteLLM image, starts the container, and verifies the stack.

Server Compass deploying the LiteLLM template on the VPS

Step 8

Confirm LiteLLM is running

After deployment finishes, return to the Apps tab and confirm the LiteLLM app is marked Running with its application URL available.

LiteLLM template running in the Server Compass Apps tab

Step 9

Open LiteLLM in the browser

Click Open Application or open the application URL in a browser. The LiteLLM admin UI confirms the LLM gateway is reachable.

The deployed LiteLLM admin UI loaded in a browser

After LiteLLM Opens

Do not expose LiteLLM directly to the public internet without HTTPS, a strong master key, and an additional access-control layer.
Use a VPN, IP allowlist, or authenticated reverse proxy for production LLM gateway access.
Configure LLM provider API keys through the LiteLLM admin UI and keep them out of screenshots and docs.
Keep the LiteLLM image updated for security and provider-routing fixes.
Create virtual keys for teams instead of sharing the master key.

Verified Result

The LiteLLM admin UI loaded successfully in a browser.

Download Server Compass Docs

LiteLLM deployment questions

What does the LiteLLM template deploy?

It deploys the LiteLLM container with a PostgreSQL database, persistent data volumes, generated master key, and generated database password.

Which port did the tutorial use?

The tutorial used host port 4000, which maps to the LiteLLM web UI on container port 4000.

Why does the browser verification stop at the first web UI screen?

A fresh LiteLLM deployment is considered reachable when the admin UI loads. The tutorial does not publish the generated master key or database password.

Should this become a blog post?

No. The deployment guide should live on the LiteLLM template detail page and be linked from the reusable template deployment docs page.

Why Self-Host LiteLLM?

LiteLLM is a unified API proxy that lets you call 100+ LLM providers through a single OpenAI-compatible interface. Self-hosting your LLM proxy means centralizing API key management, enforcing rate limits, and tracking costs across all your AI applications — without exposing credentials to a third-party service.

Single API for OpenAI, Anthropic, Google, Azure, and 100+ providers

Centralized API key management — developers never see raw keys

Built-in spend tracking, rate limiting, and usage analytics

Automatic fallback between providers for higher reliability

OpenAI-compatible API — works with any existing OpenAI SDK integration

LiteLLM vs Alternatives

LiteLLM vs OpenRouter

OpenRouter is a hosted proxy with markup fees. Self-hosted LiteLLM uses your own API keys with zero intermediary costs.

LiteLLM vs Direct API calls

Direct calls scatter API keys across apps. LiteLLM centralizes management, adds fallback logic, and provides unified logging.

LiteLLM vs Amazon Bedrock

Bedrock locks you into AWS. LiteLLM is provider-agnostic and lets you switch between any LLM without code changes.

Why Deploy LiteLLM with Server Compass?

Server Compass deploys LiteLLM with secure environment variable handling for your API keys. It sets up the proxy with persistent configuration so your model routing rules and spend limits survive container updates.

Download Server Compass

After Deployment

After deploying LiteLLM with Server Compass, complete these steps to finish setup

Configure model providers in config

Test the proxy endpoint

Use OpenAI-compatible API calls

Need help? Check out our documentation for detailed guides.

LiteLLM FAQ

Common questions about self-hosting LiteLLM

How do I deploy LiteLLM with Server Compass?

Simply download Server Compass, connect to your VPS, and select LiteLLM from the templates list. Fill in the required configuration and click Deploy. The entire process takes under 3 minutes.

What are the system requirements for LiteLLM?

LiteLLM requires a minimum of 1024MB RAM. We recommend a VPS with at least 2048MB RAM for optimal performance. Any modern Linux server with Docker support will work.

Can I migrate my existing LiteLLM data?

Yes! Server Compass provides volume mapping that allows you to import existing data. You can also use standard LiteLLM backup and restore procedures.

How do I update LiteLLM to the latest version?

Server Compass makes updates easy. Simply click the Update button in your deployment dashboard, and the latest LiteLLM image will be pulled and deployed with zero downtime.

Is LiteLLM free to self-host?

LiteLLM is open-source software. You only pay for your VPS hosting (typically $5-20/month) and optionally Server Compass ($29 one-time). No subscription fees or per-seat pricing.

Related Templates

View all Development

PocketBase

Open-source backend in a single file with realtime database, auth, and file storage

Appwrite

Open-source backend-as-a-service - self-hosted Firebase alternative

Parse Server

Open-source backend framework with dashboard

Supabase

Full Supabase self-hosted with Kong, GoTrue Auth, Realtime, and Studio

Ready to Self-Host LiteLLM?

Download Server Compass and deploy LiteLLM to your VPS in under 3 minutes. No Docker expertise required.

Download Server Compass