PiAPI
HomeWorkspace
HomeWorkspace
Join Discord
  1. Seedance
  • Get Started
    • Overview
    • Quickstart
    • Make Instruction: How to Use PiAPI to Build a Workflow on Make?
  • Endpoints
    • Flux
      • Flux with LoRA and Controlnet
      • Available LoRA and Controlnet
      • Flux API with Redux Variation, Fill, Inpaint and Outpaint
      • Create Task
        • Text to Image
        • Image to Image
        • Kontext
      • Get task
    • Gemini
      • Gemini-2.5-flash-image
      • Nano Banana Pro
      • Nano Banana 2
      • Get task
    • Qwen Image
      • Text to Image
      • Image Edit
      • Get task
    • Z-Image
      • Text to Image
      • Get task
    • Seedream
      • Seedream 5 Lite
      • Get Task
    • Faceswap
      • Multi Faceswap
      • Image Faceswap
      • Video Faceswap
      • Get Task
    • Kling
      • Lipsync With PiAPI Kling API Examples
      • Motion Brush With PiAPI Kling API Example
      • Kling Elements Video Generation API
      • Kling Effects Video Generation
      • Cancel Task
        • Cancel Task
        • Cancel Tasks
      • Get Task
      • Create Task
      • Kling Virtual Try-On
      • Kling Effects
      • Kling Sound
      • Kling Avatar
      • Kling Motion Control
      • Kling Turbo
      • Kling 3.0
    • Kling omni
      • Kling o1
      • Kling 3.0 omni
      • Get Task
    • Omni Human
      • OmniHuman 1.5
      • Get task
    • Seedance
      • Moderation and Penalty
      • Model Comparison
      • Seedance 2 preview
        POST
      • Seedance 2
        POST
      • Video Watermark Remover
        POST
      • Get task
        GET
    • Veo3
      • Veo3 Text to Video
      • Veo3 Image to Video
      • Veo3.1 Text to Video
      • Veo3.1 Image to Video
      • Get task
    • Sora2
      • Sora2-preview Text to Video
      • Sora2 Text to Video
      • Sora2-Pro Text to Video
      • Sora2 Remove Watermark
      • Get task
    • WanX
      • Generate WanX Task with LoRA Using PiAPI
      • Available LoRA Types for Wanx
      • Use Cases for Wanx LoRA
      • Use Cases for Wanx Control Camera
      • Create Task
      • Get Task
    • Wan
      • Wan2.6 Text to Video
      • Wan2.6 Image to Video
      • Get task
    • Hailuo
      • Generate Video
      • Get Task
    • Skyreels
      • Create Task
      • Get Task
    • Framepack
      • Create Task
      • Get Task
    • Hunyuan Video
      • How to Make a Hunyuan API Call
      • Available Hunyuan Lora models
      • Get Task
      • Generate Video
    • Luma Dream Machine
      • Create Task
      • Get Task
    • LLM
      • How To Avoid Timeouts in Completion API
      • LLM API | Basic Completions
    • Suno(service stopped)
      • Music(service stopped)
      • Lyrics(service stopped)
      • Get task
    • Song(Udio)
      • Song API Task Creation Examples
      • [Udio] Song Extend
      • Get Task
      • Create Task
      • [Udio] Generate Lyrics
    • Mmaudio
      • Get Task
      • Generate Audio
    • DiffRhythm
      • Generate Audio
      • Get Task
    • Ace Step
      • Create Task
        • Text to Audio
        • Audio to Audio
        • Audio Edit
        • Audio Extend
      • Get Task
    • TTS
      • Zeroshot Text-to-Speech F5-TTS
      • Get Task
    • Trellis
      • Trellis Create Task
      • Trellis2 Create Task
      • Get Task
    • Joycaption
      • Image Caption
      • Get Task
    • Midjourney
      • PiAPI Penalties on Midjourney Usage
      • Detailed Explaination on Midjourney Task Result
      • Midjourney V7 API Instructions
      • Create Task
        • Imagine
        • Upscale
        • Variation
        • Reroll
        • Describe
        • Seed
        • Blend
        • Inpaint
        • Outpaint
        • Pan
      • Cancel Task
        • Cancel Task
        • Cancel Tasks
      • Get Task
    • AI Hug
      • Get Task
      • Create Task
    • Tools
      • File Upload API
      • Remove Background API
      • Remove Background-Get Task
      • Segment With Prompt API
      • Segment With Prompt API-Get Task
      • Image Upscale(Super Resolution) API
      • Image Upscale-Get Task
      • Video Upscale
      • Video Upscale-Get Task
      • Video Remove Background
      • Video Remove Background-Get task
    • PiAPI Account Management
      • PiAPI Account Info
      • Task List Info
      • User Task History
    • GPT image
      • GPT-image API
    • Claude Code
      • Claude Code Usage Guide
  • Resources
    • Change Log
    • Output Storage
    • Unified API Schema
    • Webhook
    • Bulk Generation Service
    • Billings
    • PiAPI MCP Server
    • Workspace Manual
      • Host-your-account (HYA) | Back-up Account
      • Host-your-account (HYA) | Debug Checklist
      • Host-your-account (HYA) | Connected Account Status
    • Announcements
      • PiAPI 2025 January 1st Pricing Update
      • The discontinued support for midjourney
      • Sunsetting Suno
  • Schemas
    • Schemas
      • motion brush
      • Create Task
      • camera control
      • Cancel Params
      • Float2 Point
      • Control Points
      • txt2video-1.3b
      • txt2video-14b
      • txt2video-14b-lora
      • img2video-14b
      • img2video-14b-lora
      • img2video-14b-keyframe
      • img2video-14b-control-camera
      • wan22-txt2video-14b
      • wan22-img2video-14b
      • hunyuan-txt2video-lora
      • Trellis API/text-to-3D
      • Trellis API/image-to-3D
      • Trellis2 API/image-to-3D
      • Kling omni multi shot
      • VideoGenerationRequest
      • TaskRequest
      • VideoGenerationResponse
      • TaskConfig
      • TaskInput
      • TaskResponse
      • ErrorResponse
    • Response
      • Unified-Task-Response
    • RequestBodies
      • Unified-Task-Request-Body
    • config
    • control_net_setting
    • lora_setting
  1. Seedance

Seedance 2 preview

POST
https://api.piapi.ai/api/v1/task

Overview#

Seedance 2.0 provides high‑quality video generation from text prompts, with optional image references to control subject appearance or style. VIP models additionally support video and audio references. This document describes the available models, pricing, usage guidelines, and the syntax for referencing media in your prompts.
Currently available models:
seedance-2-preview (standard)
seedance-2-fast-preview (standard)
seedance-2-preview-vip (supports video/audio references)
seedance-2-fast-preview-vip (supports video/audio references)
For a detailed comparison of all Seedance models (including the non-preview variants), see Model Comparison.

Pricing#

ModelResolutionPrice per second
seedance-2-preview480p$0.10
seedance-2-preview-vip720p$0.20
seedance-2-preview-vip1080p$0.50
seedance-2-fast-preview480p$0.08
seedance-2-fast-preview-vip720p$0.16
For VIP models with video references, billing is based on input video duration × (price per second/2) + output duration × price per second.
Price modification was applied on 2026/04/22.

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/Audio references: Only available on VIP models (seedance-2-preview-vip / seedance-2-fast-preview-vip). Maximum 3 videos, maximum 3 audios (total audio duration ≤ 15s). Audio references require at least one image or video reference.
Aspect ratio: The aspect ratio of the reference image takes precedence over the aspect ratio specified in the request parameters.

Using References in Prompts#

When you include media in your request, you can reference them directly in the text prompt using @typeN placeholders, where N is the 1‑based position within that media type.

Syntax#

@image1, @image2, … – reference images
@video1, @video2, … – reference videos (VIP only)
@audio1, @audio2, … – reference audios (VIP only)
You can use multiple references in a single prompt to indicate different subjects or transitions.
The engine automatically converts @imageN / @videoN / @audioN to the upstream API format for compatibility. You may also use the Chinese format (@图片N / @视频N / @音频N) 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

Video + Audio reference (VIP)#

The character in @image1 dances to @audio1 in the scene from @video1

Validation#

If your prompt references media 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 References (VIP Models Only)#

VIP models support video references via the video_urls array. You can provide up to 3 video URLs. The input videos are used as references for the generation.

How it works#

Provide video URLs in the video_urls array (maximum 3).
Total video reference duration must not exceed 15.4 seconds.
Billing is based on (input video total duration + output duration) × price per second.
You may combine video references with image references (via image_urls) and audio references (via audio_urls).
The input video must pass a content safety review.

Audio References (VIP Models Only)#

VIP models support audio references via the audio_urls array. You can provide up to 3 audio URLs.

How it works#

Provide audio URLs in the audio_urls array (maximum 3).
Total audio duration must not exceed 15 seconds.
Audio references require at least one image or video reference — audio-only submissions are not supported.
Supported formats: mp3, ogg, wav, m4a, aac.

Tips#

Use publicly accessible media URLs (e.g., hosted on a CDN or cloud storage).
Keep reference media short (5–15 seconds) for best results.
Describe the desired output clearly in your prompt.

Request

Header Params

Body Params application/json

Examples
{
    "model": "seedance",
    "task_type": "seedance-2-preview",
    "input": {
        "prompt": "A woman sings and strums her guitar",
        "duration": 5,
        "aspect_ratio": "16:9"
    },
    "config": {
        "webhook_config": {
            "endpoint": "https://webhook.site/440dc876-c92a-4ef7-a3c5-2f4a8f528601",
            "secret": ""
        }
    }
}

Request Code Samples

Shell
JavaScript
Java
Swift
Go
PHP
Python
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
Request Request Example
Shell
JavaScript
Java
Swift
cURL
curl --location --request POST 'https://api.piapi.ai/api/v1/task' \
--header 'X-API-Key;' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "seedance",
    "task_type": "seedance-2-preview",
    "input": {
        "prompt": "A woman sings and strums her guitar",
        "duration": 5,
        "aspect_ratio": "16:9"
    },
    "config": {
        "webhook_config": {
            "endpoint": "https://webhook.site/440dc876-c92a-4ef7-a3c5-2f4a8f528601",
            "secret": ""
        }
    }
}'

Responses

🟢200Success
application/json
Body

Examples
{
    "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"
}
Modified at 2026-04-22 13:03:13
Previous
Model Comparison
Next
Seedance 2