POST /v1/videos/generations returns a job id immediately and queues the render; you poll GET /v1/videos/generations/{id} until status is completed, at which point the MP4 is in data[0].b64_json.
A 2-second clip typically takes 50–90 seconds end-to-end. Jobs are retained for 24 hours after completion. Find video-capable models by their category of video — see model discovery.
Submit a job
202 Accepted with { "id": "...", "status": "queued", "created": 1748902000 }.
Poll for the result
Status values
Request fields
Polling cadence
Poll every 5–10 seconds; faster polling won’t speed up the render and counts against your rate limit. The poll endpoint is cheap (no GPU cost) but still rate-limited per key.Billing
Video models bill per output second. Read the active rate fromGET /v1/pricing — find the row for your model, where pricing_type is per_second, and take unit_price_usd. The billing reference explains how that becomes a charge.