Skip to main content
Become an Edge Provider by connecting compatible devices and applications to ZeroGPU. Contribute compute from idle devices and make that capacity available for distributed AI inference across the ZeroGPU network. You add a ZeroGPU Edge SDK to an app you already ship. While your users run the app, their device becomes an inference node: it downloads a small model, registers with the network, and serves inference tasks locally. ZeroGPU handles routing, model assignment, and verification; you don’t run any servers.

​
Edge SDKs

Android SDK

Connect supported Android devices to the ZeroGPU edge network.

Chrome / Web SDK

Contribute compute from websites and Chrome extensions running in supported browsers.

Telegram Mini Apps SDK

Connect Telegram Mini Apps to ZeroGPU and contribute available device compute to the edge network.

macOS SDK

Connect supported Apple Silicon devices to the ZeroGPU edge network.

​
How it works

1

Add your app

Register your app in the Edge Operator Portal and submit it for approval.
2

Get your SDK key

Once your app is approved, copy its SDK key (zgpu-sdk-…) from the portal.
3

Integrate the SDK

Add the SDK for your platform and start it with your SDK key. Devices register themselves automatically.
4

Contribute compute

Devices running your app serve inference tasks. Track activity and earnings in the portal.

Get started

Set up your first Edge Provider integration.