Seedance 2.0 Mini API

POST /v1/tasks

All models are called through the Unified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name	seedance-2.0-mini
Type	Video generation (text-to-video)
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

The cost-efficient member of ByteDance's Seedance 2.0 family — text-to-video and image-to-video in one model, with native synced audio and image/video/audio multimodal references, up to 720P and 4–15s, built for scalable short-video production.

Production guidance

For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Cost-efficient short-video at scale

Much cheaper than flagship Seedance 2.0, with a lower rate when reference videos are provided — ideal for social clips, ad drafts, and batch short-video production.

resolutiongenerate_audio

Image-to-video / first-last-frame

Provide a first frame (and optional last frame) to animate a still image and control start/end frames — great for product-image-to-video and concept demos.

first_frame_urllast_frame_url

Multimodal reference generation

Guide character, style, and motion with reference images, videos, and audio for more controllable, consistent output.

reference_image_urlsreference_video_urls

Clips with native audio

Generate visuals and synced audio in one pass, skipping post-production dubbing; turn audio off to cut cost when sound is not needed.

generate_audioduration

Request parameters

POST https://api.hiapi.ai/v1/tasks

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
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-mini",
  "input": {
    "prompt": "A cat walking on the beach at sunset, cinematic",
    "resolution": "720p",
    "duration": 5,
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "seedance-2.0-mini",
  "input": {
    "prompt": "A cat walking on the beach at sunset, cinematic",
    "resolution": "720p",
    "duration": 5,
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "seedance-2.0-mini",
  "input": {
    "prompt": "A cat walking on the beach at sunset, cinematic",
    "resolution": "720p",
    "duration": 5,
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value seedance-2.0-mini.

example seedance-2.0-mini

input object required

Business parameters. Put Seedance 2.0 Mini-specific configuration here.

prompt string required

Text prompt describing the video to generate.

resolution enum required

Output resolution. 480p is faster; 720p balances speed and quality. The pricing tier depends on resolution and whether reference videos (reference_video_urls) are provided.

default 720p enum: 480p720p

duration integer required

Clip length in seconds, 4–15. Billed per second (longer costs more).

default 5

aspect_ratio enum optional

Output aspect ratio.

default 16:9 enum: 1:14:33:416:99:1621:9adaptive

generate_audio boolean optional

Whether to generate native audio synced to the video.

default true

first_frame_url string optional

First-frame image URL (providing it triggers image-to-video). · Format: jpeg / png / webp / bmp / tiff / gif · Aspect ratio (w/h): 0.4–2.5 · Edge length: 300–6000 px · Size: under 30 MB each · Mutually exclusive with reference images / videos

last_frame_url string optional

Last-frame image URL (used with first frame), same requirements as first frame. · Format: jpeg / png / webp / bmp / tiff / gif · Aspect ratio: 0.4–2.5 · Edge length: 300–6000 px · Size: under 30 MB each

reference_image_urls string[] optional

Reference image URL list (mutually exclusive with first frame / reference videos). · Count: together with first/last frames must not exceed 9 · Format: jpeg / png / webp / bmp / tiff / gif · Aspect ratio (w/h): 0.4–2.5 · Edge length: 300–6000 px · Size: under 30 MB each

reference_video_urls string[] optional

Reference video URL list, up to 3, total duration ≤ 15s. Each video: · Format: mp4 / mov · Resolution: 480p / 720p · Single clip: 2–15s · Aspect ratio: 0.4–2.5 · Edge length: 300–6000 px · Total pixels: 409600–927408 (w×h) · FPS: 24–60 · Size: under 50 MB each

reference_audio_urls string[] optional

Reference audio URL list, up to 3, total duration ≤ 15s. Each clip: · Format: wav / mp3 · Single clip: 2–15s · Size: under 15 MB each

callback object optional

Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.

url string required

Required when callback is set; HTTPS URL that receives terminal task notifications.

example https://your-domain.com/hiapi/callback

when enum optional

Callback trigger timing. Use final.

default final enum: final

Example requests

Text-to-video (with audio)

Audio on, 720p, 5 seconds — for social clips that need sound.

Request body

{
  "model": "seedance-2.0-mini",
  "input": {
    "prompt": "Neon-lit cyberpunk street on a rainy night, slow camera push-in, vivid reflections on wet pavement, cinematic",
    "resolution": "720p",
    "duration": 5,
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}

Image-to-video (first-frame driven)

Provide a first-frame image to animate a still — great for product-image-to-video and concept demos.

Request body

{
  "model": "seedance-2.0-mini",
  "input": {
    "prompt": "Camera slowly pulls back, clouds drifting between mountain peaks, golden morning light",
    "first_frame_url": "https://your-domain.com/first-frame.jpg",
    "resolution": "720p",
    "duration": 5,
    "generate_audio": false
  }
}

Getting the result

The response returns a taskId immediately without waiting for generation to finish.
In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
When status=success, download the generated video from output[].url.
When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

What resolutions and durations does Seedance 2.0 Mini support?

Resolutions 480p / 720p (up to 720P), durations 4–15 seconds. Pricing is tiered by resolution and whether reference videos are provided, billed per second. See the pricing page for live rates. View pricing

How is price calculated? Are reference videos cheaper?

Pricing is tiered by resolution and whether reference videos (reference_video_urls) are provided, billed per second. Providing reference videos gives a lower per-second rate; omitting them is higher. generate_audio (whether audio is generated) does not affect price. See the pricing page for exact rates. View pricing

A generation failed citing an audio content issue — what now?

With audio on, a few prompts can trip the official audio content moderation and fail the task. Set generate_audio to false and retry — it usually generates fine (visuals only, no audio).

How do I do image-to-video?

Pass first_frame_url (and optional last_frame_url) in input to switch to image-to-video; or use reference_image_urls / reference_video_urls / reference_audio_urls for multimodal references. First frame, reference images, and reference videos are mutually exclusive modes.