Put your idle GPUs to work.
Run the Venom daemon on a spare GPU box and serve requests from organisations that allow public nodes. Your machine opens no inbound port, and the cloud checks every job, so trust is earned from the work itself.
Payouts to hosts are not built yet. The waitlist hears first when they are.
What it looks like today
- A GPU that trained one model or ran one project now sits idle most of the day.
- Renting it out means opening ports to strangers and trusting them with your machine.
- Buyers have no way to tell an honest host from one that serves a cheaper model, so nobody trusts a new one.
What you run
The same daemon an organisation runs for its own team, joined to the public pool instead.
- An enginevLLM or SGLang with the venom-sampler/1 logits processor, or llama.cpp behind the venom-llamacpp shim, serving the exact model artifact of a registry entry. Ollama is not admitted. Docs
- The daemonThe orchestrator in mesh mode, joined with a public-pool token. It dials out to the cloud and takes work over that connection. Docs
- A preflightBefore your daemon advertises a model, it runs the registry's golden cases against your engine locally and checks token ids, outputs and weight hashes, so a misconfiguration is caught before it costs you trust. Docs
- Your priceYou set a price per million input and output tokens for each model in the orchestrator's pricing config. Your daemon advertises it, and buyers see it in the public node catalogue. Docs
How a public job reaches you
Public requests are relayed by the cloud, never sent straight to you, so it can time each job and check the receipt. An auditor replays a sample on reference hardware.
An organisation's request
Venom Cloud
pub.Your daemon
Your engine
An auditor replays a sample of jobs on reference hardware, and your daemon moves between trust states
probationEvery new key starts here, with a small share of traffic and 10% of jobs audited.
goodAfter 1,000 witnessed jobs and 10 passed audits with no confirmed failure.
quarantinedAfter a confirmed failed audit. No public traffic until reviewed.
barredAfter a second confirmed failure in 30 days. The key is never readmitted.
What is true today
Each line links the page of the docs that shows it.
- Every public job carries a signed receipt, and the cloud checks it against what the client received.docs/mesh/public-mesh
- Jobs are picked for audit by a secret published only after each hour, so a daemon cannot steer which ones are checked.docs/mesh/public-mesh
- Your daemon sees the key, tenant and key group only as pub, and a session id only as an HMAC.docs/mesh/public-mesh
- A prompt that looks like it contains a secret is never sent to a public daemon.docs/mesh/public-mesh
- Your daemon can read its own quality record and its audits' verdicts with their evidence.docs/mesh/public-mesh
- The daemon installs in one step and starts with one click, no Docker.docs/deploy/desktop-daemon
Earnings: counted today, paid later
For each public job your daemon serves, once the cloud has witnessed it, the cloud books a credit at your listed price and shows the daily totals on your daemon's page in the console. Payouts, identity checks and held balances are not built yet, so nothing is paid out today.
- You set the price per million tokens for each model you serve
- Only witnessed jobs count
- The waitlist hears first when payouts open
Questions people ask first
Can I get paid for hosting today?
Is my machine exposed?
What hardware do I need?
Who sends me requests?
What happens if an audit fails?
Get on the list for public hosting
Tell us what GPUs you have. We will write when payouts open.