How do I deploy LiteLLM on Railway?

You can deploy LiteLLM on Railway by clicking the "Deploy Now" button on this page. Railway will automatically set up all the necessary services and configurations for you.

What are the system requirements?

Railway handles all the infrastructure requirements. You only need a web browser to deploy and manage your application.

Is this template free to use?

Yes, this template is free to use within your existing Railway account.

Can I customize this template?

Yes, you can fully customize this template. After deployment, you will have full control of what you've deployed in your Railway project.

How do I get support for this template?

You can get support through our community forum: litellm-70029935, or click "Get template help" for this template for more assistance.

Deploy and Host LiteLLM on Railway

LiteLLM is a unified API gateway that provides OpenAI-compatible endpoints for over 100 LLM providers, including OpenAI, Anthropic, Azure, Cohere, Mistral, Google Gemini, and AWS Bedrock. It includes spend tracking, rate limiting, and an admin dashboard.

About Hosting LiteLLM

LiteLLM runs as an API proxy that translates OpenAI-format requests to provider-specific formats behind the scenes. This template deploys the LiteLLM proxy alongside PostgreSQL for storing API keys, spend logs, and model configurations, and Redis for response caching and rate limiting. All three services are wired together automatically. The master key and salt key are auto-generated. Once deployed, you add your LLM provider API keys through the admin UI or API, create virtual keys with per-key budgets and rate limits, then point your applications at the LiteLLM endpoint as a drop-in replacement for any OpenAI SDK.

Common Use Cases

Routing LLM requests across multiple providers through a single OpenAI-compatible endpoint so you can switch models without code changes
Tracking and limiting LLM spend across teams and projects with per-key budgets and usage analytics
Load balancing requests across model deployments with automatic fallback to alternative providers on failure

Dependencies for LiteLLM Hosting

PostgreSQL (included in this template)
Redis (included in this template)

Deployment Dependencies

Implementation Details

Models can be added three ways: through the admin UI at your deployment URL, via the /model/new API endpoint, or by editing config.yaml in the repo. When STORE_MODEL_IN_DB=True (the default), model configurations added through the UI or API persist in PostgreSQL and survive redeployments without repo changes.

Resource Usage

This template deploys 3 services (LiteLLM proxy, PostgreSQL, Redis) with persistent volumes. Resource usage scales with API request volume and caching activity — expect moderate baseline costs from running three services.

Why Deploy LiteLLM 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 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.