Seedance 2 Mini

Seedance 2 轻量版视频生成,仅支持多模态参考模式(图/视频/音频),480p-720p,低成本草稿。

CokeAPI 接入 Seedance 2 Mini 轻量版视频模型。默认是异步任务: POST 创建后拿到 task_id,再通过 GET /v1/generations/{task_id} 轮询直到 succeeded。

图生视频提示:生成接口不再接收内联 base64 图片数据。请先使用文件上传接口上传参考图片获取 URL,再传入 image_with_roles 或 video_with_roles 或 audio_with_roles。

模型 ID: seedance-2-mini

调用示例

curl https://cokeapi.com/v1/video/generations \
  -H "Authorization: Bearer sk-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2-mini",
    "client_business_id": "order_20260616_001",
    "prompt": "保持图片1中的人物形象,参考视频1的运镜和音频1的节奏,生成一段室内口播短视频",
    "duration": 10,
    "aspect_ratio": "16:9",
    "image_with_roles": [
      {"url": "https://cdn.cokeapi.com/uploads/2026/05/17/ref.jpg", "role": "reference_image"}
    ],
    "video_with_roles": [
      {"url": "https://cdn.cokeapi.com/uploads/2026/05/17/ref.mp4", "role": "reference_video"}
    ],
    "audio_with_roles": [
      {"url": "https://cdn.cokeapi.com/uploads/2026/05/17/ref.mp3", "role": "reference_audio"}
    ],
    "resolution": "480p"
  }'

TASK_ID="01HX..."
curl https://cokeapi.com/v1/generations/$TASK_ID \
  -H "Authorization: Bearer sk-xxxxxxxx"

import httpx, time

BASE = "https://cokeapi.com/v1"
HEADERS = {"Authorization": "Bearer sk-xxxxxxxx"}

r = httpx.post(
    f"{BASE}/video/generations",
    headers=HEADERS,
    json={
        "model": "seedance-2-mini",
        "client_business_id": "order_20260616_001",
        "prompt": "Keep the person from image 1, reference video 1 camera movement and audio 1 rhythm",
        "duration": 10,
        "aspect_ratio": "16:9",
        "image_with_roles": [
            {"url": "https://cdn.cokeapi.com/uploads/2026/05/17/ref.jpg", "role": "reference_image"}
        ],
        "video_with_roles": [
            {"url": "https://cdn.cokeapi.com/uploads/2026/05/17/ref.mp4", "role": "reference_video"}
        ],
        "audio_with_roles": [
            {"url": "https://cdn.cokeapi.com/uploads/2026/05/17/ref.mp3", "role": "reference_audio"}
        ],
        "resolution": "480p",
    },
    timeout=60,
)
task_id = r.json()["id"]

while True:
    r = httpx.get(f"{BASE}/generations/{task_id}", headers=HEADERS, timeout=30)
    data = r.json()
    if data["status"] in ("succeeded", "failed", "refunded"):
        print(data)
        break
    time.sleep(5)

const BASE = "https://cokeapi.com/v1";
const KEY = process.env.COKEAPI_KEY;

const create = await fetch(`${BASE}/video/generations`, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "seedance-2-mini",
    client_business_id: "order_20260616_001",
    prompt: "Keep the person from image 1, reference video 1 and audio 1",
    duration: 10,
    aspect_ratio: "16:9",
    image_with_roles: [
      {url: "https://cdn.cokeapi.com/uploads/2026/05/17/ref.jpg", role: "reference_image"},
    ],
    video_with_roles: [
      {url: "https://cdn.cokeapi.com/uploads/2026/05/17/ref.mp4", role: "reference_video"},
    ],
    audio_with_roles: [
      {url: "https://cdn.cokeapi.com/uploads/2026/05/17/ref.mp3", role: "reference_audio"},
    ],
    resolution: "480p",
  }),
});
const { id: taskId } = await create.json();

while (true) {
  const poll = await fetch(`${BASE}/generations/${taskId}`, {
    headers: { "Authorization": `Bearer ${KEY}` },
  });
  const data = await poll.json();
  if (["succeeded", "failed", "refunded"].includes(data.status)) {
    console.log(data);
    break;
  }
  await new Promise((r) => setTimeout(r, 5000));
}

请求参数

参数	类型	必填	默认值	说明
model	string	是	—	`seedance-2-mini`
prompt	string	是	—	视频内容描述,中文≤500字,英文≤1000词
client_business_id	string	否	—	客户侧业务 ID,可用于查询状态
duration	int	是	—	时长(秒): `4` / `8` / `10` / `12` / `15`
aspect_ratio	string	否	—	宽高比: `21:9` / `16:9` / `4:3` / `1:1` / `3:4` / `9:16`
image_with_roles	object[]	否	—	带角色的图片数组,每项含 `url` 和 `role`
video_with_roles	object[]	否	—	带角色的视频数组,每项含 `url` 和 `role`
audio_with_roles	object[]	否	—	带角色的音频数组,每项含 `url` 和 `role`
resolution	string	否	`720p`	分辨率: `480p`/`720p`
seed	int	否	—	随机种子
callback_url	string	否	—	回调地址,需配合 `trace_id` 使用
trace_id	string	否	—	调用方透传 ID,需配合 `callback_url` 使用

image_with_roles 格式

[
  {"url": "https://example.com/ref.jpg", "role": "reference_image"}
]

支持的 role 值:

reference_image — 参考图(最多 9 张)

seedance-2-mini 不支持 first_frame 和 last_frame 角色。

video_with_roles 格式

[
  {"url": "https://example.com/ref.mp4", "role": "reference_video"}
]

role 固定为 reference_video。最多 3 条。

audio_with_roles 格式

[
  {"url": "https://example.com/ref.mp3", "role": "reference_audio"}
]

role 固定为 reference_audio。最多 3 段。需配合图片或视频参考输入。

输入组合规则

输入形态	说明
文本 + 参考图	多模态参考生视频
文本 + 参考视频	视频参考生视频
文本 + 参考图 + 参考音频	多模态参考生视频
文本 + 参考图 + 参考视频 + 参考音频	多模态参考生视频

seedance-2-mini 不支持纯文生视频，必须至少提供一种参考素材（图/视频/音频）。

响应

创建任务 (`POST`)

{
  "id": "video_abc123def456",
  "task_id": "video_abc123def456",
  "object": "video.generation.task",
  "status": "queued",
  "progress": 0,
  "model": "seedance-2-mini",
  "kind": "video",
  "mode": "text_to_video",
  "created": 1768380224
}

查询任务 (`GET /v1/generations/{task_id}`)

完成后:

{
  "id": "video_abc123def456",
  "task_id": "video_abc123def456",
  "object": "video.generation.task",
  "status": "succeeded",
  "progress": 100,
  "model": "seedance-2-mini",
  "kind": "video",
  "mode": "text_to_video",
  "result": {
    "id": "video_abc123def456",
    "object": "video.generation",
    "created": 1768380224,
    "model": "seedance-2-mini",
    "data": [
      {
        "url": "https://cdn.cokeapi.com/v/video_abc123def456.mp4",
        "duration_ms": 10000,
        "width": 1280,
        "height": 720
      }
    ]
  },
  "created": 1768380224
}

任务状态说明

状态	说明
queued	任务已排队等待处理
running	任务正在处理中
succeeded	任务已完成
failed	任务失败
refunded	任务失败已退款

计费

按 6 秒基准档计费,超过 6 秒按 10 秒档计费(费用 = 基准价 × 10/6)。

分辨率	6 秒基准价	10 秒价
480p	$0.057	$0.095
720p	$0.057	$0.095
768p	$0.114	$0.19

图生视频(带参考图)按 i2v 价目计费:

分辨率	6 秒基准价(i2v)	10 秒价(i2v)
480p	$0.068	$0.113
720p	$0.138	$0.23

失败任务不计费,自动退款。价格为 2026-07 快照,以模型列表页实时价目为准。

注意事项

seedance-2-mini 仅支持多模态参考模式,不支持纯文生视频和首帧/尾帧模式。
seedance-2-mini 不支持生成同步音频 (generate_audio)。
duration 为必填,仅支持固定值: 4 / 8 / 10 / 12 / 15。
最多支持 9 张参考图、3 条参考视频、3 段参考音频。
失败的任务不计费,会自动返还预扣点数。

本页目录