enable_sync_mode set to true (some models do not support this parameter, but you still need to query the result by id), you must call the Query Result endpoint to retrieve the final output.
data.id – the unique identifier of the predictiondata.urls[0].get – a ready-to-use GET URL that already embeds the idResponse Example
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
prompt | string | ✅ Yes | - | - | Text prompt that describes the video to generate. |
image | file | ❌ No | - | - | Optional image reference that guides generation. The image must match the target video’s resolution (size). |
duration | string | ❌ No | 4 | 4812 | Clip duration in seconds. Defaults to 4 seconds. |
size | string | ❌ No | 720x1280 | 720x12801280x7201024x17921792x1024 | Output resolution formatted as width x height. Defaults to 720x1280. Note: 1024x1792 and 1792x1024 are only supported by sora2-pro model. |
| Error Code | Error Name | Description |
|---|---|---|
| 401 | Unauthorized | API key is missing or invalid |
| 403 | Forbidden | Your API key doesn’t have permission to access this resource, or insufficient balance for the requested operation |
| 429 | Too Many Requests | You’ve exceeded your rate limit |
| 500 | Internal server error | An internal server error occurred |
| 503 | Content policy violation | Content blocked due to safety concerns (actual status code is 400) |