POST /v1/videos/generations
API Reference
POST /v1/videos/generations
Create a video generation job (async)
POST
POST /v1/videos/generations
Request body
The namespaced model ID, e.g.
fal/kling-2. See Video models.Video description. Maximum 4000 characters.
Duration in seconds. If you don’t send it, we use the model default. Per-model cap (see catalog).
Video ratio. Examples:
16:9, 9:16, 1:1, 4:5. Support depends on the model.Response (immediate, ~100ms)
The job_id. Use it for polling.
Usually
processing. Rare but possible failed if the submission to the provider blew up.The model id you requested.
Examples
⚠️ About cost
When you create the job you are NOT charged yet. The charge happens when the job transitions tocompleted. If it fails, there’s no charge.
Safety cap: your balance is validated at submit — if it’s ≤ 0 we return 402 insufficient_balance before creating the job.
Next step
GET /v1/videos/{id}
Poll the job status until it reaches
completed.