Overview

Seedance 2.0 provides high‑quality video generation from text prompts, with optional image references to control subject appearance or style, and optional video input for video editing. This document describes the available models, pricing, usage guidelines, and the syntax for referencing images and videos in your prompts.

Currently available models:

seedance-2-preview

seedance-2-fast-preview

Pricing

Model	Mode	Price per second
seedance-2-preview	Text/Image to Video	$0.15
seedance-2-fast-preview	Text/Image to Video	$0.08
seedance-2-preview	Video Edit	$0.15
seedance-2-fast-preview	Video Edit	$0.08

For Video Edit mode, the duration parameter is ignored. Since this mode edits the original video, the output video length equals the input video length. Billing is based on the actual output video duration.

Note

Peak hours: From 09:00 to 15:00 GMT, Seedance experiences high traffic. During this period, queue times may extend to several hours.

Reference images: The API supports using one or more images as references in your prompts. See Using Image References for syntax. Maximum 9 images.

Video edit: The API supports editing an existing video by providing it via video_urls. See Video Edit below.

Aspect ratio: The aspect ratio of the reference image takes precedence over the aspect ratio specified in the request parameters. (We have noticed the issue that the aspect ratio parameter is currently not taking effect and are working on a fix.)

Using Image References in Prompts

When you include images in your request, you can reference them directly in the text prompt using the @imageN placeholder, where N is the 1‑based position of the image in the request (e.g., the first uploaded image is @image1).

Syntax

@image1, @image2, … – reference the image at the corresponding position.

You can use multiple references in a single prompt to indicate different subjects or transitions.

The engine automatically converts @imageN to the upstream API format 【@图片N】 for compatibility. You may also use the Chinese format directly if preferred.

Examples

Single image reference

The cat in @image1 walks through a garden

Morphing effect

@image1 transforms into @image2

Multi‑subject scene

The whale in @image1 meets the ninja in @image2

Validation

If your prompt references an image that was not provided (e.g., you use @image3 but only two images are supplied), the request will be rejected with a 400 Bad Request error.

Video Edit

You can provide a video via the video_urls array to enable video edit mode. In this mode, Seedance edits the original video based on the transformations described in your prompt. The output video has the same length as the input video.

How it works

Provide exactly one video URL in the video_urls array.

The duration parameter is ignored in this mode — the output video length equals the input video length, since this mode edits the original video rather than generating a new one.

You may combine video edit with image references (via image_urls) to control subject appearance in the edited video (e.g., replace a character).

The input video must pass a content safety review. If the video is rejected, the task will fail with an error message indicating the media did not pass the security check.

Tips

Use publicly accessible video URLs (e.g., hosted on a CDN or cloud storage).

Keep input videos short (5–15 seconds) for best results.

Describe the desired transformation clearly in your prompt (e.g., style changes, lighting, effects, character replacement).

application/json

Body

Examples

Task created (pending)Video edit completed

{
    "code": 200,
    "data": {
        "task_id": "07ed43de-465d-43b1-b62c-44249b14d818",
        "model": "seedance",
        "task_type": "seedance-2-preview",
        "status": "pending",
        "config": {
            "service_mode": "",
            "webhook_config": {
                "endpoint": "",
                "secret": ""
            }
        },
        "input": {
            "prompt": "A woman sings and strums her guitar",
            "duration": 5,
            "aspect_ratio": "16:9"
        },
        "output": null,
        "meta": {
            "created_at": "2026-02-27T13:33:26.10346684Z",
            "started_at": "0001-01-01T00:00:00Z",
            "ended_at": "0001-01-01T00:00:00Z",
            "usage": {
                "type": "llm",
                "frozen": 0,
                "consume": 7500000
            },
            "is_using_private_pool": false
        },
        "detail": null,
        "logs": [],
        "error": {
            "code": 0,
            "raw_message": "",
            "message": "",
            "detail": null
        }
    },
    "message": "success"
}

Seedance 2 preview

Overview

Pricing

Note

Using Image References in Prompts

Syntax

Examples

Single image reference

Morphing effect

Multi‑subject scene

Validation

Video Edit

How it works

Tips

Request

Request Code Samples

Responses

Seedance 2 preview

Overview#

Pricing#

Note#

Using Image References in Prompts#

Syntax#

Examples#

Single image reference#

Morphing effect#

Multi‑subject scene#

Validation#

Video Edit#

How it works#

Tips#

Request

Request Code Samples

Responses

Overview

Pricing

Note

Using Image References in Prompts

Syntax

Examples

Single image reference

Morphing effect

Multi‑subject scene

Validation

Video Edit

How it works

Tips