Pyo
Pyo Cloud
AIby PyoOfficial template

Deploy LiteLLM on your own servers

One OpenAI-compatible gateway to 100+ model providers, with keys, budgets and usage tracking.

Get started LiteLLM website

What Pyo sets up

Image
ghcr.io/berriai/litellm:v1.83.14-stable
Reached
Web app, on a domain you add
Database
Uses a Postgres database, connected when you deploy
Runs as
Stateless service
Replicas
1
Requests
0.25 vCPU · 512 MiB
Limits
2 vCPU · 2 GiB
Storage
None
Health check
HTTP /health/liveliness

How to deploy it

  1. 1

    Install Pyo

    Run the setup command on your server.

  2. 2

    Choose LiteLLM

    Open Templates in the dashboard and pick it. Pyo fills in sensible defaults.

  3. 3

    Deploy

    Pick a server and deploy. Pyo runs it and follows the rollout.

Ports

  • http 4000/HTTPInternal until you add a domain

Good to know

  • Sign in to the admin UI at /ui with the user admin and LITELLM_MASTER_KEY as the password; add models and keys there.
  • Keep LITELLM_SALT_KEY as it is; it encrypts the provider keys you save.
  • Other services call it at http://<service>:4000, like the OpenAI API.

Related templates

All templates

Get Pyo running on your server

Run Pyo on any machine, from your laptop or VPS to a dedicated server or homelab.

curl -fsSL https://pyo.dev/install.sh | bash
View on GitHub