Pricing

Aquaduck encrypts data in transit and is designed to keep sensitive account and billing information off contributor devices. For organizations with stricter requirements, private Aquaduck deployments can run entirely on company-owned hardware.

Aquaduck taps compute that is already available across the network instead of relying solely on centralized data centers. We're rebuilding the supply layer for AI inference around distributed hardware. Contributors expand the network's available intelligence, while Aquaduck intelligently routes inference to deliver strong model performance at competitive pricing.

Aquaduck turns distributed hardware into a single intelligence network. Contributors expand the network's available intelligence and earn for participating, while builders access it through a unified API. It's a new approach to AI infrastructure that aligns everyone who helps power the network.

Aquaduck handles machine health automatically. Devices that go offline are removed from routing within seconds, and workers automatically reconnect after network interruptions. If a device drops during an in-flight request, the request fails fast so it can be retried immediately. Aquaduck is continuously improving how retries and recovery are handled across the network.