提交任务

请求体与视频生成（OpenAI 兼容）完全一致：prompt、image、duration、size 等字段平铺在顶层，没有 content 数组。唯一差别是路径多一个 s。

The body is identical to Video generation (OpenAI-compatible): prompt, image, duration, size, and the other fields sit flat at the top level, with no content array. The only difference is the extra s in the path.

OpenAI 兼容结构只有 prompt 与 image 两个创作字段，能表达的场景比豆包原生少。需要首尾帧、参考图、视频编辑或延长时，用豆包原生通道提交，任务查询仍然走同一个任务状态接口。

The OpenAI-compatible schema has only two creative fields, prompt and image, so it expresses fewer scenarios than Doubao native. For first-and-last frames, reference images, video editing, or extension, submit through the Doubao native channel; task polling still uses the same task status endpoint.

更多状态码与重试建议见错误码与限流，常见报错的排查步骤见常见问题。

For more status codes and retry guidance see Error codes and rate limits; for troubleshooting steps on common errors see the FAQ.

两个路径指向同一套逻辑，差异只在路径拼写：

已有代码用哪个都能跑。新项目建议用复数形式，与 OpenAI 生态保持一致。

Both paths point at the same logic; the difference is only the spelling:

Existing code works with either. New projects should use the plural form to stay consistent with the OpenAI ecosystem.

以下视频模型均可通过本接口提交任务，清单只列各厂商最新一代，实际可用范围以你的账号分组为准：

各型号的能力差异：

2.0 家族里 fast 与 mini 只支持 480p 与 720p，4K 仅 2.0 标准版可用。

Every video model below can be submitted through this endpoint; the list shows only each vendor's latest generation, and what your account group actually allows takes precedence:

Differences between model families:

Within the 2.0 family, fast and mini support only 480p and 720p; 4K is available only on the 2.0 standard model.

基础提交

/v1/videos 与 /v1/video/generations 参数完全一致，只是路径多了一个 s。两条都能用，选一条固定下来即可。

带首帧

image 按首帧处理，提示词描述后续运动。首帧建议与目标画面比例一致，否则会被裁剪。

异步回调

服务端处理耗时较长时用回调，避免客户端长时间轮询。

Basic submission

/v1/videos and /v1/video/generations take identical parameters; the path just has an extra s. Both work — pick one and stick to it.

With a first frame

image is treated as the first frame, and the prompt describes the motion afterward. The first frame should match the target aspect ratio, or it gets cropped.

Async callback

When server-side processing takes a long time, use a callback to avoid long client-side polling.