Earn on every token your node serves.A globally distributed AI compute network.
Connect a node (a GPU, Apple Silicon, or a cloud account) and the network routes paying inference traffic to it. Or call the network from any OpenAI SDK and pay a fraction of flagship-API prices. Same account does both.
How it works
Two sides, one network.
Run a model. Use a model. Or both — same account, same credits.
Run a model. Earn credits.
- 1Register a node — a GPU you own, Apple Silicon, or a cloud account you already pay for.
- 2The network routes inference requests to your node.
- 3Credits accrue per token served — spend them, or save them.
Use the network. Spend per token.
- 1Sign up and grab an API key from your dashboard.
- 2Point any OpenAI SDK at our endpoint — change the base URL, that's it.
- 3Start with $5 in free credits. Need more? Run a node and earn them.
For providers
Turn the compute you have into income.
Run a model on a GPU you own, or harness a cloud account you already pay for. Either way, the network routes paying traffic to your node and credits your account on every token served.
Earn on every token
Every successful request pays the operator who served it — revenue flows to the node that did the work, not a flat seat fee or a capped credit you'll never spend.
Any node will do
Run a node on a GPU you own — discrete, Apple Silicon, or a CPU box — or on a cloud account you already pay for. Either way, the network routes paying traffic to it.
A fraction of flagship-API prices
Open models cost a small fraction of what closed-flagship APIs charge for comparable capability — that's why demand exists, and why your node has something to serve.
Your compute. Their tokens. Your income.
Register a nodeFeatures
Built like the internet, not like a vendor.
OpenAI-compatible
Drop-in compatible. Point any OpenAI SDK at our endpoint, swap the base URL — everything else stays the same.
Compute is the currency
Bring a node — a GPU, Apple Silicon, or a cloud account — earn credits per token served, and spend those same credits on your own inference. One account, both sides.
Built-in reliability
Multiple providers serve each model. The network routes around failures and retries automatically.
No single vendor
A marketplace of providers, not a closed silo. Models live across independent operators.
Distributed cluster
Every request lands on the freest node.
A planet-scale cluster you don't own — routed by availability, not ranking. The gateway picks the least-loaded healthy candidate on every call.
Beta access
Start with $5. Earn the rest.
Sign up for the beta and get $5 in credits to try the network — no card required. Want more? Run a node and earn credits on every token it serves, then spend them on your own inference.
Free to sign up. Bring a model to earn more credits when you’re ready.