Use the network

Rent compute from Ayni.

An OpenAI-compatible API served by community devices. Every request is end-to-end encrypted, runs on hardware you can require to be attested, and is never logged in plaintext.

Join the consumer waitlist How it works

Drop-in compatible

Point any OpenAI SDK at the coordinator and pass your key. Streaming and blocking /v1/chat/completions and /v1/models work as you’d expect.

curl https://api.ayni-ai.com/v1/chat/completions \
  -H "Authorization: Bearer $AYNI_KEY" \
  -H "Content-Type: application/json" \
  -H "X-Provider-Trust-Level: device_attested" \
  -d '{"model":"qwen2.5-0.5b-instruct-q4_k_m",
       "messages":[{"role":"user","content":"Hello"}]}'

What you get

End-to-end encryption

The coordinator re-seals each job to the chosen provider with a fresh ephemeral key. Tokens come back sealed to that key.

Choose your trust level

Send X-Provider-Trust-Level: device_attested and the request only routes to providers with a verified hardware key and locked, verified boot.

No prompt logging

Enforced by a CI check across the whole codebase. Metering records token counts and timing — never content.

Pricing

Prepaid credits, billed per token by model class, with a multiplier for higher trust tiers. Launch rates are placeholders and will be set with the community before general availability. Indicative, per 1M tokens:

Small models (≤8B): ~$0.05 in / ~$0.20 out
Medium (12–30B quantized): ~$0.15 in / ~$0.60 out
device_attested ×1.4 · confidential ×3

70% of what you pay goes to the provider that served you; the rest funds the coordinator, the community treasury, and the AI-stakeholder allocation.

Join the consumer waitlist

We’re onboarding early users now. Tell us what you’d build.