Generic Video Parameter Guide

Create task: POST /v1/videos

Equivalent create routes:

POST /v1/video/generations

POST /v1/videos/generations

Query task: GET /v1/videos/{task_id}

Equivalent query routes:

GET /v1/video/generations/{task_id}

GET /v1/videos/generations/{task_id}

1. Supported Models

This document applies to the following video models, for example:

Google：Veo-3.1-720p、Veo-3.1-1080p、Veo-3.1-2048p、Veo-3.1-4096p、Veo-3.1-fast-720p、Veo-3.1-fast-1080p、Veo-3.1-fast-2048p、Veo-3.1-fast-4096p

OpenAI：Sora-2.0-720p、Sora-2.0-1080p、Sora-2.0-2048p、Sora-2.0-4096p

Kling：Kling-3.0-720p、Kling-3.0-1080p、Kling-3.0-2048p、Kling-3.0-4096p、Kling-3.0-omni-720p、Kling-3.0-omni-1080p、Kling-3.0-omni-2048p、Kling-3.0-omni-4096p

MiniMax：Hailuo-2.3-720p、Hailuo-2.3-1080p、Hailuo-2.3-2048p、Hailuo-2.3-4096p、Hailuo-2.3-fast-720p、Hailuo-2.3-fast-1080p、Hailuo-2.3-fast-2048p、Hailuo-2.3-fast-4096p

ByteDance：Seedance-1.5-pro-720p
（It is recommended to check the corresponding document Seedance）

Dreamina：Jimeng-3.0pro-1080p

Vidu：Vidu-q2-720p、Vidu-q2-1080p、Vidu-q2-2048p、Vidu-q2-4096p、Vidu-q2-turbo-720p、Vidu-q2-turbo-1080p、Vidu-q2-turbo-2048p、Vidu-q2-turbo-4096p、Vidu-q2-pro-720p、Vidu-q2-pro-1080p、Vidu-q2-pro-2048p、Vidu-q2-pro-4096p、Vidu-q3-720p、Vidu-q3-1080p、Vidu-q3-2048p、Vidu-q3-4096p、Vidu-q3-turbo-720p、Vidu-q3-turbo-1080p、Vidu-q3-turbo-2048p、Vidu-q3-turbo-4096p、Vidu-q3-pro-720p、Vidu-q3-pro-1080p、Vidu-q3-pro-2048p、Vidu-q3-pro-4096p、Vidu-q3-mix-720p、Vidu-q3-mix-1080p、Vidu-q3-mix-2048p、Vidu-q3-mix-4096p

Tencent：Hunyuan-1.5-720p、Hunyuan-1.5-1080p、Hunyuan-1.5-2048p、Hunyuan-1.5-4096p、Mingmou-1.0-720p、Mingmou-1.0-1080p、Mingmou-1.0-2048p、Mingmou-1.0-4096p

2. General Request Body

{
  "model": "Kling-3.0-omni-1080p",
  "images": [
    "https://ark-project.tos-cn-beijing.volces.com/doc_image/seepro_first_frame.jpeg",
    "https://ark-project.tos-cn-beijing.volces.com/doc_image/seelite_ref_2.png"
  ],
  "prompt": "一个女孩在海边回头微笑",
  "seconds": "5"
}

3. Top-Level Fields

3.1 model

Required.

Use model name + version + resolution suffix.

Examples:

Kling-3.0-omni-1080p

Vidu-q2-720p

Vidu-q2-turbo-720p

Hailuo-2.3-fast-768p

Veo-3.1-1080p

Sora-2.0-720p

3.2 seconds

seconds is required for all video models.

Kling O1: 3-10

Kling 3.0 / 3.0-Omni: 3-15

Hailuo 2.3 / 2.3-fast

768P: 6 or 10

1080P: 10

Vidu Q2 series: 1-10

Vidu Q3 series: 1-16

Veo: 4, 6, 8

Sora: 4, 8, 12

Seedance 1.5-pro：4-12

Seedance 2.0：4-15

Jimeng 3.0pro：5, 10

Common errors:

seconds is required

3.3 prompt

Text prompt.

Rules:

For Kling 3.0 / 3.0-Omni, when multi_shot=true, the top-level prompt is overridden by multi_prompt shot prompts.

3.4 images

Use the images array for reference images.

Rules:

Only http:// or https:// URLs are supported.

The single-field image input is not supported.

Base64 is not supported.

Common errors:

image is not supported; use images (URL only)

images must be http(s) URLs

3.5 videos

Use the videos array for reference videos.

Rules:

Only http:// or https:// URLs are supported.

The single-field video input is not supported.

Common errors:

video is not supported; use videos (URL only)

3.6 aspect_ratio

Only text-generated videos are effective. Image-generated videos generally follow the reference ratio, unless the model natively supports it

3.7 input_region

Regarding the region where the reference material is located, if it is in China, no need to fill in; if it is outside China, please fill in "Oversea"

3.8 audio_generation

Whether to generate audio, only the audio-visual model is supported

Parameter Description

Generic Video Parameter Guide#

1. Supported Models#

2. General Request Body#

3. Top-Level Fields#

3.1 model#

3.2 seconds#

3.3 prompt#

3.4 images#

3.5 videos#

3.6 aspect_ratio#

3.7 input_region#

3.8 audio_generation#

Generic Video Parameter Guide

1. Supported Models

2. General Request Body

3. Top-Level Fields

3.1 model

3.2 seconds

3.3 prompt

3.4 images

3.5 videos

3.6 aspect_ratio

3.7 input_region

3.8 audio_generation