Seedance

Seedance 2 is a video generation family with audio sync, first/last-frame control, and multimodal references.

API surface

Operation	Endpoint	Mode
Video generation task	POST /v1/async/videos/generations	Async only

Models

Model id	Notes
seedance-2	Full quality. Resolutions up to 4k. seconds 4–15.
seedance-2-fast	Faster. Max 720p. seconds 4–15.
seedance-2-mini	Lowest cost. Max 720p. seconds only 4 / 8 / 10 / 12 / 15. n must be 1.

Pricing

Billed as n × seconds × rate(resolution) credits. Default resolution is 720p.

Model	480p	720p	1080p	4K
seedance-2-mini	4/sec	8/sec	—	—
seedance-2-fast	6/sec	13/sec	—	—
seedance-2	8/sec	16/sec	38/sec	78/sec

Example: seedance-2 + 720p + seconds=5 + n=1 → 16 × 5 = 80 credits.

Request fields

Send the common fields at the top level. Put the model-specific controls listed below inside providerOptions.

Field	Type	Required	Description
model	string	Yes	seedance-2, seedance-2-fast, seedance-2-mini
prompt	string	Yes	Describe subjects, actions, camera motion, and style; 1–2,000 characters on Pixapi.
seconds	integer	Yes	Standard/Fast: integers 4–15; Mini: 4, 8, 10, 12, 15. No implicit default on Pixapi.
resolution	string	No	480p / 720p; seedance-2: 1080p / 4k. Pixapi default: 720p.
n	integer	No	Default 1; only integer 1 is supported.
image	string / string[]	No	Public image URL(s), up to 9 references. For explicit first/last frames use image_with_roles instead.
providerOptions	object	No	Model-specific options; see the table below.

providerOptions

All fields in this table are nested inside providerOptions, not alongside model.

Field	Type	Description
aspect_ratio	string	21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive. Default 16:9; image-to-video follows the input image ratio.
generate_audio	boolean	Default true; generate synchronized sound. false produces silent video.
seed	integer	Controls randomness; matching seeds can give similar but not identical videos.
image_with_roles	object[]	Each item {url,role}; roles first_frame (≤1), last_frame (≤1), reference_image (≤9). Do not mix first/last frames with reference media. Use this or top-level image, not both.
video_urls	string[]	Up to 3 public reference videos, 480p–720p; total duration >1.8 and <15.2 seconds. Cannot be combined with first/last frames.
audio_urls	string[]	Up to 3 public audio references, total ≤15 seconds; must accompany image/video references, not first/last-frame mode.
return_last_frame	boolean	Default false; also return the last-frame image.
tools	object[]	Web search enhancement: [{"type":"web_search"}].
nsfw_check	boolean	Optional prompt/image moderation; default false.

Input rules

Keep Pixapi IDs (seedance-2, etc.); Pixapi requires a non-empty prompt even in image-to-video mode.

Example

cURL

curl https://api.pixapi.ai/v1/async/videos/generations \
  -H "Authorization: Bearer $PIXAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedance-2",
  "prompt": "A shiba inu running through neon-lit rainy streets",
  "n": 1,
  "seconds": 5,
  "resolution": "720p",
  "providerOptions": {
    "generate_audio": true,
    "aspect_ratio": "16:9"
  }
}'

Python

import os
import requests

response = requests.post(
    "https://api.pixapi.ai/v1/async/videos/generations",
    headers={
        "Authorization": f"Bearer {os.environ['PIXAPI_KEY']}",
        "Content-Type": "application/json",
    },
    json={
    "model": "seedance-2",
    "prompt": "A shiba inu running through neon-lit rainy streets",
    "n": 1,
    "seconds": 5,
    "resolution": "720p",
    "providerOptions": {
        "generate_audio": True,
        "aspect_ratio": "16:9"
    }
},
)
response.raise_for_status()
task = response.json()
print(task["id"])

JavaScript

const response = await fetch('https://api.pixapi.ai/v1/async/videos/generations', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.PIXAPI_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "seedance-2",
  "prompt": "A shiba inu running through neon-lit rainy streets",
  "n": 1,
  "seconds": 5,
  "resolution": "720p",
  "providerOptions": {
    "generate_audio": true,
    "aspect_ratio": "16:9"
  }
}),
});

if (!response.ok) {
  throw new Error(await response.text());
}

const task = await response.json();
console.log(task.id);

Go

package main

import (
  "bytes"
  "fmt"
  "io"
  "net/http"
  "os"
)

func main() {
  body := []byte(`{
  "model": "seedance-2",
  "prompt": "A shiba inu running through neon-lit rainy streets",
  "n": 1,
  "seconds": 5,
  "resolution": "720p",
  "providerOptions": {
    "generate_audio": true,
    "aspect_ratio": "16:9"
  }
}`)

  req, err := http.NewRequest(
    "POST",
    "https://api.pixapi.ai/v1/async/videos/generations",
    bytes.NewBuffer(body),
  )
  if err != nil {
    panic(err)
  }
  req.Header.Set("Authorization", "Bearer "+os.Getenv("PIXAPI_KEY"))
  req.Header.Set("Content-Type", "application/json")

  resp, err := http.DefaultClient.Do(req)
  if err != nil {
    panic(err)
  }
  defer resp.Body.Close()

  result, _ := io.ReadAll(resp.Body)
  fmt.Println(string(result))
}

Response

Pixapi returns a submitted task. Poll GET /v1/tasks/{id} for the final result.