Seedance 2.0 API
Commercial useHOTSeedance 2.0 is a multimodal AI video model by ByteDance, optimized for fast and realistic video generation. It supports high-quality virtual human video creation with strong multi-shot consistency, enabling more lifelike and cinematic outputs across scenes.
With efficient generation speed, Seedance 2.0 typically averages around ~5 minutes per generation, while Seedance 2.0 Fast averages around ~4 minutes, making it a reliable choice for scalable content production.
Lowest cost starts at $0.06/s
480p: 12 credits/s - Video to Video - (input + output) × 12
480p: 19 credits/s - Text/Image to Video - Output seconds × 19
720p: 25 credits/s - Video to Video - (input + output) × 25
720p: 41 credits/s - Text/Image to Video - Output seconds × 41
1080p: 62 credits/s - Video to Video - (input + output) × 62
1080p: 102 credits/s - Text/Image to Video - Output seconds × 102
USD estimates use $0.005/credit with the best annual plan.
Core request fields
Keep the payload predictable while still allowing rich multimodal control.
{
"model": "bytedance/seedance-2",
"input": {
"prompt": "A serene beach at sunset with waves gently crashing on the shore, palm trees swaying in the breeze, and seagulls flying across the orange sky",
"first_frame_url": "https://templateb.aiquickdraw.com/custom-page/akr/section-images/example2.png",
"last_frame_url": "https://templateb.aiquickdraw.com/custom-page/akr/section-images/example3.png",
"reference_image_urls": [
"https://templateb.aiquickdraw.com/custom-page/akr/section-images/example1.png"
],
"reference_video_urls": [
"https://templateb.aiquickdraw.com/custom-page/akr/section-images/example1.mp4"
],
"reference_audio_urls": [
"https://templateb.aiquickdraw.com/custom-page/akr/section-images/example1.mp3"
],
"return_last_frame": false,
"generate_audio": false,
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 15,
"web_search": false
}
}Use Seedance 2.0 for generation
The playground, request sample, request fields, and pricing on this page follow the selected model type.
View detailed API docsOpen the full API documentation for endpoints, authentication, task polling, and payload details. /models/seedance-2.0.md
promptstringThe text prompt used to generate the video. Required field. (Min length: 3, Max length: 20000 characters)first_frame_urlstringFirst frame image url or asset://{assetId}last_frame_urlstringEnd frame image url or asset://{assetId}reference_image_urlsarrayEnter a list of image URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj).reference_video_urlsarrayEnter a list of video URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj) .reference_audio_urlsarrayEnter a list of audio URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj) .return_last_framebooleanWhether to return the last frame of the video as an image.generate_audiobooleanWhether to generate audio for the video.resolutionenumVideo resolution - 480p for faster generation, 720p for balance, 1080p for High-quality video, 4K Ultra-High Definition, delivering perfect visual details. (480p, 720p, 1080p, 4k)aspect_ratioenumVideo aspect ratio configuration. Required field. (1:1, 4:3, 3:4, 16:9, 9:16, 21:9, adaptive)durationnumberVideo duration in 4-15 seconds.web_searchbooleanUse online searchnsfw_checkerbooleanDefaults to false. You can set it to false based on your needs. If set to false, our content filtering will be disabled, and all results will be returned directly by the model itself.What Seedance 2.0 API adds to your video workflow
The page follows the same API-first structure as the reference: test the model, understand the fields, then move into integration.
Multimodal references
Combine prompts with images, videos, and audio so the model can follow subject identity, motion, rhythm, and visual style.
Multi-shot consistency
Create short cinematic sequences with steadier characters, camera logic, and scene continuity across cuts.
Reference-driven motion
Use source clips to guide camera movement, action timing, transitions, and high-impact visual pacing.
Audio-aware creation
Upload audio references or enable generated audio for beat-matched clips, music videos, and synced storytelling.
From playground test to production request
A compact integration path for teams that want to validate output quality before wiring the API into an app.
1. Prepare request
Choose Seedance 2.0 or Seedance 2.0 Fast, then add prompt text and any reference media your workflow needs.
2. Submit generation
Call the API with your account key, model id, duration, resolution, aspect ratio, and media URLs.
3. Poll and render
Track the task until it succeeds, then retrieve the generated video URL for your app, campaign, or pipeline.
What you can create with Seedance 2.0 API
Use the API when your product needs repeatable AI video output, not just a one-off playground result.
Built for real API workflows
Account-gated execution
Users sign in, submit jobs, and consume credits through the existing SdanceAI generation flow.
Reference media handling
The studio supports uploaded reference media, direct URLs, previews, and form/API payload editing.
Scalable model choice
Switch between standard and fast Seedance 2.0 modes based on quality, cost, and latency needs.
Seedance 2.0 API questions
What is Seedance 2.0 API best for?
It is best for short, cinematic AI video generation where prompt control and reference media matter, including product videos, social clips, motion replication, and multi-shot storytelling.
What is the difference between Seedance 2.0 and Seedance 2.0 Fast?
Seedance 2.0 focuses on higher-quality output and stronger creative control. Seedance 2.0 Fast is optimized for faster iteration and scalable batch workflows.
Can I use images, video, and audio in one request?
Yes. The Seedance 2.0 workflow supports text plus mixed reference inputs, including images, video clips, and audio references.
Where can I test it before integrating?
Use the playground on this page to test prompts, references, resolution, aspect ratio, duration, and API payload behavior before moving into production.
What new features does Seedance 2.0 API introduce?
Seedance 2.0 introduces broader multimodal control with text, image, video, and audio references. It is designed for better motion guidance, stronger scene consistency, and more predictable cinematic output.
How is Seedance 2.0 API different from typical AI video generators?
Many video generators rely mostly on prompt interpretation. Seedance 2.0 is more reference-driven, so it can use source media to guide camera motion, action timing, transitions, subject style, and pacing.
How many references can I upload in a Seedance 2.0 API project?
The workflow supports up to 9 image references, up to 3 video references, and up to 3 audio references. Reference video and audio inputs should stay within the documented duration limits.
Does Seedance 2.0 API support voice guidance and lip-sync generation?
The model workflow supports audio-aware generation. You can use audio references for rhythm and pacing, and enable generated audio where supported by the selected version and request settings.
What video length and duration options are available?
Seedance 2.0 is built for short-form clips, commonly in the 4 to 15 second range. Duration, aspect ratio, and resolution should be selected together to match your target output format.
Can I use Seedance 2.0 API for commercial projects?
This page is configured for commercial-use workflows. For production use, review your account plan, credit balance, model availability, and any applicable content policy requirements.
Turn Seedance 2.0 into your video workflow
Open the generator, test a prompt, then use the API docs when you are ready to wire Seedance 2.0 into production.