Use the network

Run a workload on Ayni.

Submit a batch of items, get one price and a completion estimate, and Ayni fans it out across benchmarked community devices. Every request is end-to-end encrypted, runs on hardware you can require to be attested, and is never logged in plaintext. Single requests still work the OpenAI way.

Join the consumer waitlist How it works

Quote a workload

POST /v1/workloads returns a price and an ETA built from the live supply — how many eligible devices are online and what they actually sustain. Accepting it runs the batch and charges you once, at the quoted price.

curl https://api.ayni-ai.com/v1/workloads \
  -H "Authorization: Bearer $AYNI_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen2.5-0.5b-instruct-q4_k_m",
       "items":[{"messages":[{"role":"user","content":"Summarize: ..."}],"max_tokens":160},
                {"messages":[{"role":"user","content":"Summarize: ..."}],"max_tokens":160}]}'
# -> { "id":"wl_...", "estimate":{"eta_seconds":...,"eligible_nodes":3},
#      "price":{"total_usd":0.42,"breakdown_usd":{...}}, "accept_url":"/v1/workloads/wl_.../accept" }

curl -X POST https://api.ayni-ai.com/v1/workloads/wl_.../accept \
  -H "Authorization: Bearer $AYNI_KEY"
# -> { "object":"workload.result", "items":[ ...in submission order... ], "charged_usd":0.42 }

Prefer to place the batch yourself? POST /v1/batch takes the same items, fans them out immediately, and meters pay-as-you-go.

Not in a hurry? Add "spot": true. Spot workloads run on whatever capacity on-demand traffic leaves free — priced at 60% of on-demand, with a wider completion-time band, and Ayni may interrupt and requeue them.

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.