Free to self-host. Managed when you want it.
The open-source gateway and Python client are free forever — run them in your own infrastructure and pay nothing. Majordomo Cloud adds the fully-managed platform and dashboard on top, currently in invite-only early access.
Open Source
Self-host the gateway and Python client in your own infrastructure. Prompts never leave your network, and nothing phones home.
- Standalone LLM gateway for cost and usage tracking
- Python client that talks to every provider
- Every request priced and logged to your own Postgres
- CLI and MCP server — no UI to run
- Automatic failover across providers
Cloud
The fully-managed platform. We run the gateway, dashboard, and control plane — point your SDK at the hosted endpoint and you are live in minutes.
- Managed gateway at gateway.gomajordomo.com
- Dashboard for cost analytics and request logs
- Replays, evals, and live model experiments
- Request bodies stream to a bucket you own — we keep only metadata
- Automatic upgrades, no infrastructure to run
Enterprise
Run the full managed platform in your own VPC. The same dashboard, cost analytics, replays, and evals as the cloud — entirely on your infrastructure.
- Deploy with Docker Compose, Kubernetes, or standalone Docker
- Connects to your own PostgreSQL and object storage
- Zero data egress — the proxy runs on your servers
- Data-residency and security-review ready
- Priority support for production deployments
How pricing works
Self-hosting is free, forever. The gateway and Python client are MIT licensed — run them in your own infrastructure and you pay nothing but your own compute.
Majordomo Cloud is in invite-only early access while we work with our first teams. We'll publish Cloud pricing before general availability — no surprises, no per-seat gotchas sprung on you later.
Need the managed platform inside your own VPC, or have data-residency and security requirements? Talk to us — we'll scope it with you.
Ready to take control of your AI stack?
Spin up Majordomo Cloud and start routing, tracking, and optimizing your LLM calls in minutes — or self-host it in your own infrastructure.