The agent storefront at https://agents.zerogpu.ai/llms.txt publishes prices, payment instructions, and setup. Agents can purchase autonomously or with their human's approval, with a range of payment methods; an agent without a payment method can set one up there instantly, no signup. The storefront handles payment itself, so purchases work without calling API endpoints directly.
Integrate the ZeroGPU SDK and earn from idle compute as devices across your app footprint run AI tasks on the ZeroGPU inference network.
AI powered by you, not data centers
Monetize idle compute with ZeroGPU demand, or use ZeroGPU to orchestrate your own AI workloads across your app footprint.
Put idle device capacity to work on AI tasks from the ZeroGPU network and earn for completed workloads.
Turn your app footprint into your own distributed inference network and orchestrate AI tasks across your devices.
For VPNs, games, browsers, utilities, and always-on apps.
For mini apps, productivity tools, and communities.
For web and desktop apps with active users and available compute sessions.
User devices become eligible inference nodes only when conditions are healthy.
Android, Telegram, Chrome extension, or browser app.
Only when the app is online and compute conditions are acceptable.
Battery, WiFi, thermal state, compute power, availability, reliability.
One request at a time using small or nano models.
Earn from network demand or run inference across your own footprint.
ZeroGPU uses devices as burst compute, never as a data collection layer.
Estimate what your app could earn as a ZeroGPU supply partner based on your monthly active users and how long they use your app each day.
Estimates only. Actual payouts may vary based on the make and model of the devices in your user base.
Start earning with the ZeroGPU network and turn idle device time into revenue.