Distributed Inference Network

Earn from your GPU.
Power AI inference.

Ynnova is an open inference network. Contribute your idle GPU resources and earn per token served — or consume fast, cheap LLM inference via our OpenAI-compatible API.

Become a Provider API Documentation

⚡

For GPU Providers

Have an idle GPU? Connect it to the Ynnova network and start earning per token your hardware serves.

1 Register your GPU and hardware specs
2 Deploy our lightweight worker agent
3 Traffic is routed automatically to your node
4 Earn per million tokens served

🔌

For Developers

Access distributed GPU inference with a single API key. Drop-in replacement for the OpenAI SDK.

1 Request an API key
2 Point your client to api.ynnova.eu
3 Call /v1/chat/completions as usual
4 Pay only for what you use

How it works

Your GPU resources, routed intelligently across the network.

Provider connects

GPU owners deploy a worker agent that tunnels into the Ynnova network. No port forwarding required.

Request is routed

Incoming API calls are load-balanced to the best available node based on latency and capacity.

Provider earns