> ## Documentation Index
> Fetch the complete documentation index at: https://docs.jiekou.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Veo 3.1 Video Generation (Reverse)

Veo 3.1 Video Generation and Query API

<Tip>
  This is an **asynchronous** API and will only return the async task's task\_id. You should use this task\_id to request the [Get Task Result API](/en/docs/models/reference-get-async-task-result) to retrieve the generated result.
</Tip>

## Request Headers

<ParamField header="Content-Type" type="string" required={true}>
  Enum value: `application/json`
</ParamField>

<ParamField header="Authorization" type="string" required={true}>
  Bearer authentication format: Bearer \{\{API Key}}.
</ParamField>

## Request Body

<ParamField body="size" type="string">
  Width x height. The specific values are ignored: width > height is landscape, and width \< height is portrait. Supported values: 1280x720, 720x1280
</ParamField>

<ParamField body="prompt" type="string" required={true}>
  Prompt used to guide video generation. For example: the characters in the image start running and then collide with each other
</ParamField>

<ParamField body="seconds" type="integer">
  Video duration. Currently only 8 seconds is supported.
</ParamField>

<ParamField body="watermark" type="boolean">
  Whether a watermark is required. No watermark by default.
</ParamField>

<ParamField body="input_images" type="string[]">
  Image files used to guide video generation. veo-3.1-reverse supports uploading the first frame and last frame.
</ParamField>

## Response

<ResponseField name="task_id" type="string" required={true}>
  Use the task\_id to request the [Get Task Result API](/en/docs/models/reference-get-async-task-result) to retrieve the generated output.
</ResponseField>