Hey

callback_url string

Please fill in the callback notification address for the result of this generation task. When there is a status change in the video generation task, Ark will send a callback request containing the latest task status to this address.

The content structure of the callback request is consistent with the response body of Querying the information about a video generation task.

The status returned by the callback includes the following states:

queued: In the queue.

running: The task is running.

succeeded: The task is successful. (If the sending fails, that is, the information of successful sending is not received within 5 seconds, the callback will be made three times)

failed: The task fails. (If the sending fails, that is, the information of successful sending is not received within 5 seconds, the callback will be made three times)

expired: The task has timed out. This occurs when the task has remained in the running or queued status for longer than the allowed expiration duration. The expiration duration can be set via the execution_expires_after field.

return_last_frame Boolean Default value: false

true: Returns the last frame image of the generated video. After setting this parameter to true, you can obtain the last frame image by calling the Querying the information about a video generation task. The last frame image is in PNG format, with its pixel width and height consistent with those of the generated video, and it contains no watermarks.

Using this parameter allows the generation of multiple consecutive videos: the last frame of the previously generated video is used as the first frame of the next video task, enabling quick generation of multiple consecutive videos. For specific calling examples, please refer to Generate multiple consecutive videos.

false: Does not return the last frame image of the generated video.

service_tier string Default value: default

Modification to the service tier of submitted tasks is not supported.Seedance 2.0 & 2.0 fast does not support offline inference.Specifies the service tier for processing the current request.

default: Online inference mode. This tier has lower RPM and concurrency quotas (see Model List), suitable for latency-sensitive inference scenarios.

flex: Offline inference mode. This tier provides a higher TPD quota (see Model List) at 50% of the price of the online inference tier, suitable for scenarios where low inference latency is not a critical requirement.

execution_expires_after integer Default value: 172800

The task expiration threshold. Specifies the time (in seconds) after which a submitted task will expire, calculated from its created_at timestamp.

Default: 172800 seconds (48 hours)

Valid Range: [3600，259200]

Regardless of the chosen service_tier, it is recommended to set an appropriate value based on your business scenario. Tasks exceeding the threshold will be automatically terminated and marked as expired.