Skip to content
Docs menu

Get started

Core concepts

On this page

Synchronous vs asynchronous

Chat/LLM models are synchronous: the create call returns the answer in a text field. Media models (image/video/audio) are asynchronous: the create call returns a taskId, and you poll (or use a webhook) for the result.

Task states

stateMeaning
waitingAccepted and queued upstream.
generatingThe model is running.
successDone — read resultUrls.
failFailed — read error; credits were refunded.

Result URLs

Results are returned as URLs on our own domain (/api/file?t=…) carrying an opaque, signed token. The upstream provider and its storage are never exposed to you or your users.

Credits

A task debits credits when accepted; the amount is returned as creditsCharged. A media task that fails to produce a result is automatically refunded.