A multimodal video route supporting text-only generation, endpoint frames, image/video/audio references, 4-15 seconds, and up to 4K output.
Provider: ByteDance
Category: video generation
Endpoint: /v1/tasks
Status: Available
Cost: See live page pricing
ByteDance Seedance 2.0 - ByteDance's latest video generation model with cinematic quality, exceptional motion, and native audio.
Pricing
Standard Usage
Use images to control the first and last frame.
Upload the first-frame image. Supports JPG/PNG/WebP/GIF, max 10MB
Upload the last-frame image. Supports JPG/PNG/WebP/GIF, max 10MB
Choose 4-15 seconds in 1-second steps
Upload reference audio files
Upload reference videos
Generate synchronized audio for the video
Return the last frame of the generated video
Use web search signals for generation
Ready for generation
Configure your parameters and click "Run" to see the output here.
Public model preview
Use this model preview to inspect the output format, subject motion, camera movement, and scene continuity.
A multimodal video route supporting text-only generation, endpoint frames, image/video/audio references, 4-15 seconds, and up to 4K output.
Prompt shown with this public preview
A spear-wielding warrior clashes with a dual-blade fighter in an autumn maple forest, dynamic handheld tracking, golden backlight
Choose by input method, output specifications, control surface, and budget.
Long-form video
Generate up to 30 seconds with seven aspect ratios and synchronized audio.
A multimodal video route supporting text-only generation, endpoint frames, image/video/audio references, 4-15 seconds, and up to 4K output.
Start with a text-only task, or add endpoint frames and references only when they have a clear role in the shot. seedance-2.0
These specifications reflect the current HiAPI Seedance 2.0 request contract.
Choose one control mode for the first test, then add references gradually to keep the request explainable.
This is the minimum request for an asynchronous text-to-video task. Use the API docs for task retrieval, callbacks, errors, and the complete parameter contract.
curl -X POST "https://api.hiapi.ai/v1/tasks" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.0",
"input": {
"prompt": "A spear-wielding warrior clashes with a dual-blade fighter in an autumn maple forest, dynamic handheld tracking, golden backlight",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"generate_audio": true
}
}'It is prompt-led and can also use endpoint frames or image, video, and audio references according to the active contract.
4-15 seconds, 480p, 720p, 1080p, 4k, and 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, adaptive.
Optional image, video, and audio references; generated audio
Billing follows output duration and the live tier. Resolution, mode, or audio differences are reflected by the page price and task record.
POST an asynchronous task to /v1/tasks with model set to seedance-2.0 and place parameters inside input.
Lead with subject and setting, then describe action, camera direction, and speed in time order. State no cuts for a continuous take.
Draft
5s · 720p
Final
15s · 4k
Validate subject motion and camera continuity with 5s · 720p, then move to 15s · 4k.
Check motion stability and subject consistency online, then create an asynchronous task with the same model ID: seedance-2.0.