LiteLLM logo
AI · self-hosted

LiteLLM in one click.

LiteLLM is an unified proxy for 100+ llm provider apis you can run on your own machine. Launch it in Even Stacks in one click, serve it over trusted HTTPS, and let your AI agents operate it.

What is LiteLLM?

LiteLLM is a proxy server and Python SDK providing a unified OpenAI-compatible interface to over 100 LLM providers. It supports load balancing, fallbacks, spend tracking, and per-key rate limiting.

CategoryAI
Default port4001
Container imageghcr.io/berriai/litellm:main-latest
Official sitelitellm.ai

Run LiteLLM in Even

Even Stacks launches LiteLLM as a managed container on your own machine. No compose files, no manual setup.

  1. Open the Even Stacks panel in Even. The container engine starts on demand.
  2. Find LiteLLM in the one-click services and click Launch.
  3. Even pulls the image, starts it on port 4001, and serves it over trusted HTTPS at https://litellm.localhost.

Drive LiteLLM with your AI agents

Even ships an MCP, so any agent you run inside Even (Claude Code, Codex, and more) can operate LiteLLM directly, at both the UI level and the container level.

Through the Even MCP an agent can pull a model, call the local endpoint, and wire it into a tool, all on your own hardware. It runs commands inside the container, reads its logs, and for web apps opens and clicks through the interface in Even's own browser pane. Ask once, for example "set up LiteLLM and get it ready", and the agent handles it end to end.

How agents reach it: Call any LLM via the OpenAI-compatible API at http://localhost:4001/v1/chat/completions. Manage models, API keys, and routing rules via the web UI at http://localhost:4001. Config lives in /app/config.yaml; changes via file require a container restart.

More AI services

Other one-click services you can launch in Even Stacks.