How It Works
1
Your App
Any OpenAI-compatible client sends a request
2
arbstr routes
Scores complexity, matches policy, picks cheapest provider
3
Provider responds
Inference runs on the optimal node (local, cloud, or mesh)
4
Bitcoin settles
Actual cost settled in sats via Lightning/Cashu — no tokens, no subscriptions
The Manifesto
No tokens. No staking. No governance theater. Just sats.
Every other AI marketplace invents a token. We use bitcoin — the money that already works. arbstr settles inference costs in satoshis over Lightning. Providers get paid. Buyers pay fair price. No middleman token skimming value.
Get Started
Run your own inference marketplace in under a minute.
git clone https://github.com/johnzilla/arbstr-node && cd arbstr-node
cp .env.example .env # edit with your secrets
docker compose up
curl http://localhost:8080/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer your-agent-token" \
-d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "Hello"}]}'
See the full documentation on GitHub.