Developers
One endpoint. Your model stays private.
Call private models over HTTP. Every response carries the charge and a signed receipt you can check.
{
"id": "call_01...",
"model": "mdl_example",
"version": "v1",
"status": "completed",
"output": { "score": 0.91 },
"usage": { "unit": "request", "count": 1 },
"billing": { "asset": "USDG", "amount": "0.08", "receiptId": "rcpt_..." },
"protection": { "level": "weights-tee", "attestationId": "att_..." },
"timing": { "totalMs": 0, "runtimeMs": 0 }
}Call a model
Send one authenticated POST with an idempotency key. The response tells you the outcome, the charge and the receipt to check it against.
Failed requests carry no per-request charge, and replaying the same idempotency key returns the original response.
curl -X POST 'https://api.lacren.xyz/v1/inference/mdl_example' \
-H "Authorization: Bearer $LACREN_API_KEY" \
-H 'Idempotency-Key: your-unique-id' \
-H 'Content-Type: application/json' \
-d '{"inputs":{"features":[0.12,0.43,0.72]}}'{
"id": "call_01...",
"model": "mdl_example",
"version": "v1",
"status": "completed",
"output": { "score": 0.91 },
"usage": { "unit": "request", "count": 1 },
"billing": { "asset": "USDG", "amount": "0.08", "receiptId": "rcpt_..." },
"protection": { "level": "weights-tee", "attestationId": "att_..." },
"timing": { "totalMs": 0, "runtimeMs": 0 }
}{
"error": {
"code": "LEASE_FUNDS_LOW",
"message": "Not enough funds for this request.",
"requestId": "req_...",
"retryable": false
}
}Ready to integrate?
Create access to a model in the app, create an API key, then send your first request.