Documentation

MatMul rents GPU instances from the neocloud market: pick a live offer, run a plain VM or your Docker image, and SSH in, billed from one prepaid balance. Start with how to rent a cloud GPU in 5 minutes. The guides below cover attaching your existing SkyPilot to the hosted console and sharing it, with no VPN and no inbound ports. Sharing an app from an instance with a public link is coming soon.

Get started with a GPU

1. Sign in at app.matmul.cloud and add credit on the Billing page. MatMul is prepaid; payments go through Stripe.
2. Add your SSH public key on the SSH keys page (or paste it into the launch dialog).
3. Open Launch. The list shows machines you can launch right now, cheapest first, priced per machine-hour. Which GPUs and regions are on offer depends on live supply.
4. Choose a public Docker image or the plain VM and launch. The price you confirm is a ceiling: if it goes up before the machine is created, the launch is cancelled rather than charged at the higher price.
5. When the instance is running, its page shows the SSH command. Terminate it when you're done; billing stops then.

The walkthrough How to rent a cloud GPU in 5 minutes does the same thing from the CLI. To script it, create an API key on the CLI & API page of the console.

Guides

• Share an app from your GPU: Give ComfyUI, Jupyter or a dashboard on a MatMul GPU instance a public HTTPS link (coming soon).
• Connect SkyPilot: Attach an existing SkyPilot API server (or deploy one) to the console over an outbound-only tunnel.
• Manage & share: Open your SkyPilot dashboard through the tunnel, watch environment status, and share it with teammates.
• Disconnect & remove: Disconnect a SkyPilot machine and tear down its tunnel: the two steps, and what's left behind.
• Troubleshooting: Fixes for a SkyPilot environment stuck on Pending, a 403 dashboard, or a missing connector.

What's live and what isn't

MatMul is early, so here is where each piece stands.

• Live: GPU and CPU instances, prepaid credit, SSH keys, teams with roles, the CLI, Python SDK and REST API, and SkyPilot attach.
• Preview (works, but expect rough edges): the matmul-mcp server for MCP clients such as Claude Code and Cursor.
• Coming soon: managed jobs with matmul run (built, not yet running on real GPUs) and public app links (built, switched off until abuse controls ship).
• Not built yet: inference endpoints, app links behind your MatMul sign-in, and self-serve organization invites.

SkyPilot attach

If you already run SkyPilot, you can keep it where it lives (your laptop, a VM, your cloud) and reach its dashboard from the MatMul console. MatMul provisions a private Cloudflare Tunnel for each environment; a small connector on your box dials out to it, so there's nothing to open inbound and no VPN to manage. The console then proxies your SkyPilot dashboard to you and your teammates behind single sign-on. It lives under Connections in the console sidebar.

Help

Stuck? See Support for how to reach us, and Status for known problems.