For the complete documentation index, see llms.txt. This page is also available as Markdown.

Asynchronous flow

The API is asynchronous. Every POST endpoint queues a generation job and returns 202 Accepted with a job descriptor ({ id, status, createdAt }). Poll GET /v1/presentations/{id} (recommended cadence: every 2–3 seconds) until status becomes completed (download URL in result.url) or failed (reason in error).

Typical generation time is 30–90 seconds; the hard cap is 5 minutes per job, after which jobs are marked failed with code TIMEOUT. Download links are permanent.

Last updated