Generate short video clips from text prompts.
The video generation endpoint produces short clips from a text prompt. Rendering is computationally intensive, so it runs asynchronously — you submit a job, then poll a job id for the result. The OpenAI SDK has no video resource, so call the endpoint directly with fetch.
| Status | Meaning |
|---|---|
queued | Waiting for a generation slot |
processing | Actively generating |
completed | Output ready; video.url available |
failed | Generation failed |
| Field | Description |
|---|---|
model | Video generation model slug (?modality=video). |
prompt | Text description of the desired video. |
seconds | Requested clip length, 1–60 (model-dependent maximum). |
The cost of the requested seconds is held on submission and settled on completion; a failed or timed-out job releases the full hold and charges nothing. See the video API reference.