Skip to main content
Welcome to Pinaivu — the peer-to-peer marketplace for LLM inference. Instead of routing your requests through a single centralized provider, Pinaivu connects your application to a decentralized network of GPU node operators, brokered by a cryptographically attested coordinator. Every request is verifiable, auditable, and backed by a signed routing receipt you can inspect at any time.

Quickstart

Go from zero to a working API call in under five minutes.

Authentication

Learn how to create and use your Pinaivu API key securely.

How It Works

Understand the coordinator, GPU nodes, and routing receipts.

API Reference

Explore the full OpenAI-compatible API surface.

​
Get up and running in three steps

1

Get an API key

Sign up at api.pinaivu.com, navigate to API Keys in the dashboard, and click Generate. Your key starts with sk-pnv- — copy it and store it somewhere safe.
2

Make your first request

Point any OpenAI-compatible client at https://api.pinaivu.com/v1 and pass your Pinaivu key as the Bearer token. The gateway accepts the same request format as the OpenAI Chat Completions API.
curl https://api.pinaivu.com/v1/chat/completions \
  -H "Authorization: Bearer sk-pnv-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3.2:1b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
3

Verify your inference

Every response includes a request_id. Visit explorer.pinaivu.com, paste in your request_id, and see exactly which node served your request, how it was paid, and the signed proof of inference.