Overview

Seedance 2.0 provides high-quality video generation from text prompts, with multiple modes supporting text-to-video, first/last frame control, and multi-modal omni references. This document describes the available models, pricing, modes, usage guidelines, and the syntax for referencing images, videos, and audio in your prompts.

Currently available models:

seedance-2 (Pro, higher quality)

seedance-2-fast (Fast, lower cost)

Pricing

Model	Price per second
seedance-2	$0.10
seedance-2-fast	$0.08

Cost calculation:

Without input videos: credits = unit_price × output_duration

With input videos: credits = unit_price × (total_input_video_duration + output_duration)

Duration Limits

Maximum output duration: 15 seconds (API enforces integer 4–15)

Maximum total input video duration: 15.4 seconds (sum of all input video reference durations)

Modes

The mode parameter is required. It determines how references are used and which parameters take effect.

text_to_video

Pure text-to-video generation. No references accepted.

duration: user-controlled (4-15s)

aspect_ratio: user-controlled (6 options)

first_last_frames

Use 1-2 images as the first and/or last frame of the generated video.

image_urls: 1-2 images required. Only images accepted — video and audio URLs are rejected.

duration: user-controlled (4-15s)

aspect_ratio: ignored — the output aspect ratio is determined by the reference image. Any value provided will be silently discarded.

Supported image formats: jpg, jpeg, png, webp, bmp

omni_reference

Use 1-12 mixed references (images, videos, audio) for flexible multi-modal generation.

image_urls: optional, images as style/content references

video_urls: optional, videos as motion/style references. Supported formats: mp4, mov

audio_urls: optional, audio as soundtrack (mp3/wav only, must be ≤15 seconds)

duration: user-controlled (4-15s)

aspect_ratio: user-controlled (6 options)

Audio-only is not allowed — at least one image or video reference must be provided alongside audio.

Total references (images + videos + audios) must be between 1 and 12.

Important Notes & Special Cases

Parameter behavior by mode

Parameter	text_to_video	first_last_frames	omni_reference
duration	User input (4-15)	User input (4-15)	User input (4-15)
aspect_ratio	User input (6 options)	Ignored (from image)	User input (6 options)
image_urls	Not allowed	1-2 required	optional (shared 12 max)
video_urls	Not allowed	Not allowed	optional (shared 12 max)
audio_urls	Not allowed	Not allowed	optional (shared 12 max)

Aspect ratio details

Supported values: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

Default: 16:9 (when omitted or invalid)

In first_last_frames mode, this parameter is completely ignored. The output video inherits the aspect ratio from the first reference image. Passing a value will not cause an error but will have no effect.

Duration

Range: 4 to 15 seconds (any integer)

Default: 5 seconds (when omitted or out of range)

This is different from Seedance models which only support 5/10/15.

Audio constraints

Audio references are only accepted in omni_reference mode.

Supported formats: mp3, wav only.

Maximum audio duration: 15 seconds. The upstream silently rejects audio longer than 15 seconds (the upload will time out with no explicit error message).

Audio-only submissions are rejected — at least one image or video must accompany any audio references.

Content moderation

Prompts are checked by a content moderation system before processing.

Flagged content will be rejected after a short delay. Repeated violations incur progressive credit penalties.

See: https://piapi.ai/docs/seedance-api/moderation-and-penalty

Peak hours

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

Using References in Prompts

When you include references, you can mention them in the prompt using @-syntax:

Syntax

@image1, @image2, … — reference images by position in image_urls (1-based)

@video1, @video2, … — reference videos by position in video_urls (1-based)

@audio1, @audio2, … — reference audios by position in audio_urls (1-based)

Chinese format also supported: 【@图片1】, 【@视频1】, 【@音频1】

Examples

Single image

The cat in @image1 walks through a garden

Image + video + audio

Apply @image1 artistic style with @video1 motion and @audio1 soundtrack

Morphing

@image1 transforms into @image2

Validation

If your prompt references a material that was not provided (e.g., @image3 but only 2 images supplied), the request will be rejected with a descriptive error message. The same applies to @videoN and @audioN.

Tips

Use publicly accessible URLs (e.g., hosted on a CDN or cloud storage). Signed/expiring URLs may fail.

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

Describe the desired output clearly in your prompt.

For first_last_frames, the first image controls both subject and aspect ratio of the output.

Request

Header Params

Body Params application/json

Examples

text to videofirst & last framesomni reference (video with @mention)

{
    "model": "seedance",
    "task_type": "seedance-2-fast",
    "input": {
        "prompt": "A woman sings and strums her guitar",
        "mode": "text_to_video",
        "duration": 5,
        "aspect_ratio": "16:9"
    },
    "config": {
        "webhook_config": {
            "endpoint": "https://your-webhook-endpoint.example.com/callback",
            "secret": ""
        }
    }
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

Responses

🟢200Success

application/json

Body

Examples

Task created (pending)Completed

{
    "code": 200,
    "data": {
        "task_id": "07ed43de-465d-43b1-b62c-44249b14d818",
        "model": "seedance",
        "task_type": "seedance-2-fast",
        "status": "pending",
        "config": {
            "service_mode": "",
            "webhook_config": {
                "endpoint": "",
                "secret": ""
            }
        },
        "input": {
            "prompt": "A woman sings and strums her guitar",
            "mode": "text_to_video",
            "duration": 5,
            "aspect_ratio": "16:9"
        },
        "output": null,
        "meta": {
            "created_at": "2026-04-05T13:33:26.10346684Z",
            "started_at": "0001-01-01T00:00:00Z",
            "ended_at": "0001-01-01T00:00:00Z",
            "usage": {
                "type": "point",
                "frozen": 4000000,
                "consume": 0
            },
            "is_using_private_pool": false
        },
        "detail": null,
        "logs": [],
        "error": {
            "code": 0,
            "raw_message": "",
            "message": "",
            "detail": null
        }
    },
    "message": "success"
}

Seedance 2

Overview#

Pricing#

Duration Limits#

Modes#

text_to_video#

first_last_frames#

omni_reference#

Important Notes & Special Cases#

Parameter behavior by mode#

Aspect ratio details#

Duration#

Audio constraints#

Content moderation#

Peak hours#

Using References in Prompts#

Syntax#

Examples#

Single image#

Image + video + audio#

Morphing#

Validation#

Tips#

Request

Request Code Samples

Responses

Overview

Pricing

Duration Limits

Modes

text_to_video

first_last_frames

omni_reference

Important Notes & Special Cases

Parameter behavior by mode

Aspect ratio details

Duration

Audio constraints

Content moderation

Peak hours

Using References in Prompts

Syntax

Examples

Single image

Image + video + audio

Morphing

Validation

Tips