Create Seedance Video Task

curl --request POST \
  --url https://www.jimmyai.cn/api/open-api/v1/seedance/videos \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>",
  "duration": 123,
  "images": [
    "<string>"
  ],
  "ratio": "<string>",
  "first_image": "<string>",
  "last_image": "<string>",
  "reference_videos": [
    "<string>"
  ],
  "reference_audios": [
    "<string>"
  ]
}
'

{
  "code": "20000",
  "msg": "ok",
  "data": {
    "task_id": "<string>",
    "status": "<string>",
    "model": "<string>",
    "created_at": 123
  }
}

Seedance 2.0 Video

Mini Create Video

创建 Seedance 2.0 视频生成任务。支持满血版（sd2_mx_*，按秒计费，素材须审核）、SP 经济版（seedance2.0-sp / seedance2.0-fast-sp，按分辨率按秒计费）、SP 官方版（seedance2.0-of-sp / seedance2.0-of-fast-sp，按分辨率按秒计费）、Mini 版（seedance2.0-mini，按分辨率按秒计费）、Mini 特价版（seedance2.0-mini-sp，按次计费，仅 480p/720p）、MD（seedance2.0-md / seedance2.0-fast-md，按次计费，720p，不支持音频）、Fast I2V（seedance2.0-fast-i2v，按次计费，720p，仅图片参考最多 9 张，不支持参考视频/音频）、STD 标准版（seedance2.0-std，按次计费，720p，支持音频参考）。创建后使用 GET /api/open-api/v1/videos/ 查询结果。详见 seedance/md/create、seedance/md/fast-i2v、seedance/md/std、seedance/mini/create 与 seedance/mini-sp/create 文档。

POST

api

open-api

seedance

videos

Create Seedance Video Task

curl --request POST \
  --url https://www.jimmyai.cn/api/open-api/v1/seedance/videos \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>",
  "duration": 123,
  "images": [
    "<string>"
  ],
  "ratio": "<string>",
  "first_image": "<string>",
  "last_image": "<string>",
  "reference_videos": [
    "<string>"
  ],
  "reference_audios": [
    "<string>"
  ]
}
'

{
  "code": "20000",
  "msg": "ok",
  "data": {
    "task_id": "<string>",
    "status": "<string>",
    "model": "<string>",
    "created_at": 123
  }
}

Create a Seedance 2.0 Mini video generation task. On success you receive a task_id. Poll Query Video Task until completed, then read the video URL from result.video_url.

This uses the same endpoint as Create Seedance Full Video: POST /api/open-api/v1/seedance/videos. For Full (Manxue), see the full-route doc; for SP economy, see SP Create Video.

Models

Route	Request `model`	Billing model name	Duration
Mini standard	`seedance2.0-mini`	`seedance2.0-mini-{resolution}`	4–15 s
Mini video reference	`seedance2.0-mini-video`	`seedance2.0-mini-{resolution}-video`	4–15 s

{resolution} is 480p, 720p (default), or 1080p, set via the resolution field.

Billing

Mini routes are billed per second; each resolution has its own unit price.

Item	Description
Formula	unit price (per second) × billable seconds
Unit price	See the console pricing for the billing model name (e.g. `seedance2.0-mini-720p`)
Resolution	`480p`, `720p` (default), `1080p` via `resolution`
Generation length	`duration` field, 4–15 seconds (default 5)

Billable seconds

seedance2.0-mini: billable seconds = requested duration.
seedance2.0-mini-video (with reference video): billable seconds = duration + reference video length (first item in reference_videos, rounded to nearest second). If reference duration cannot be read, falls back to duration only.

Examples

Assume seedance2.0-mini-720p unit price is $0.05/s:

Scenario	Request	Billable seconds	Cost
Image-to-video, 5 s	`model: seedance2.0-mini`, `duration: 5`, `resolution: 720p`	5	0.05 × 5 = $0.25
Video ref, 8 s + 3 s ref	`model: seedance2.0-mini-video`, `duration: 8`, 3 s reference	11	0.05 × 11 = $0.55

Actual unit prices vary by resolution and per-user pricing. Check the console before submitting tasks.

Request fields

Field	Type	Required	Description
`model`	string	Yes	`seedance2.0-mini` or `seedance2.0-mini-video`
`prompt`	string	Yes	Text prompt
`duration`	int	Yes	Length in seconds, 4–15 (default 5)
`resolution`	string	No	Output resolution: `480p`, `720p` (default), `1080p`
`ratio`	string	No	Aspect ratio, e.g. `16:9`, `9:16`, `1:1`
`images`	string[]	No	Reference images
`first_image`	string	No	First frame image
`last_image`	string	No	Last frame image
`reference_videos`	string[]	No	Reference videos; only for `seedance2.0-mini-video`
`reference_audios`	string[]	No	Reference audio; must be paired with images, video, or frames

Assets

Pass publicly reachable https:// URLs directly.
Or upload via File Upload and use the returned URL.
No Manxue asset audit required.

Constraints

images (reference mode) and first_image / last_image (frame mode) cannot be used together.
reference_videos is only supported on seedance2.0-mini-video.
reference_audios cannot be used alone; pair with images, reference video, or frames.

Examples

Mini — reference image

curl -X POST 'https://www.jimmyai.cn/api/open-api/v1/seedance/videos' \
  -H 'Authorization: Bearer sk_xxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "seedance2.0-mini",
    "prompt": "The subject slowly turns their head, hair moving in a gentle breeze",
    "duration": 6,
    "resolution": "720p",
    "ratio": "9:16",
    "images": ["https://example.com/ref-1.jpg"]
  }'

Mini — first/last frame

curl -X POST 'https://www.jimmyai.cn/api/open-api/v1/seedance/videos' \
  -H 'Authorization: Bearer sk_xxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "seedance2.0-mini",
    "prompt": "Rainy street at night, girl turns and smiles, cinematic dolly in",
    "duration": 5,
    "resolution": "1080p",
    "ratio": "16:9",
    "first_image": "https://example.com/start.png"
  }'

Mini video reference

curl -X POST 'https://www.jimmyai.cn/api/open-api/v1/seedance/videos' \
  -H 'Authorization: Bearer sk_xxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "seedance2.0-mini-video",
    "prompt": "Match the motion rhythm and camera language of the reference clip",
    "duration": 8,
    "resolution": "720p",
    "ratio": "16:9",
    "images": ["https://example.com/ref.jpg"],
    "reference_videos": ["https://example.com/motion.mp4"]
  }'

Response example

{
  "code": 0,
  "msg": "ok",
  "data": {
    "task_id": "vid_abc123",
    "status": "queued",
    "model": "seedance2.0-mini",
    "created_at": 1710000000
  }
}

Query task

curl -X GET 'https://www.jimmyai.cn/api/open-api/v1/videos/{task_id}' \
  -H 'Authorization: Bearer sk_xxx'

Task status: queued → processing → completed / failed. Read the video URL from data.result.video_url when completed.

Result URLs are kept for about 3 days. Download promptly.

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

model

string

required

Model name. Manxue: sd2_mx_720p | sd2_mx_1080p | sd2_mx_2k | sd2_mx_4k; Fast: sd2_mx_fast_720p | sd2_mx_fast_1080p; Video ref: sd2_mx_video_720p | sd2_mx_video_1080p | sd2_mx_video_2k | sd2_mx_video_4k; Video ref Fast: sd2_mx_video_fast_720p | sd2_mx_video_fast_1080p (all per-second). reference_videos only for video-series models. SP economy: seedance2.0-sp | seedance2.0-fast-sp (per-second by resolution). SP official: seedance2.0-of-sp | seedance2.0-of-fast-sp (per-second by resolution). Mini: seedance2.0-mini (per-second by resolution). Mini Special: seedance2.0-mini-sp (per-task, 480p/720p only). MD: seedance2.0-md | seedance2.0-fast-md (per-task, 720p). Fast I2V: seedance2.0-fast-i2v (per-task, 720p, image refs only). STD standard: seedance2.0-std (per-task, 720p)

prompt

string

required

Text prompt. MD route: max 5000 characters

duration

integer

required

Duration in seconds. Full 4-12; SP economy 4-15; MD 1-15; STD standard 4-15. Default 5

resolution

enum<string>

Output resolution for SP economy. Default 720p

Available options:

480p,

720p,

1080p

orientation

enum<string>

Video orientation (ratio takes precedence if set)

Available options:

landscape,

portrait

images

string[]

Reference images. Full route: asset://{assetId}; SP/MD/STD/Fast I2V: https:// URL. MD max 4; seedance2.0-fast-i2v and STD max 9. Mutually exclusive with first_image/last_image

ratio

string

Aspect ratio. MD: 16:9, 9:16, 1:1 only. STD: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16. Full route also supports 4:3, 3:4, 21:9, Adaptive

first_image

string

First frame. Full: asset://{assetId}; Economy/MD: https:// URL. MD frame mode requires last_image as well; first frame only is not supported

last_image

string

Last frame. Full: asset://{assetId}; Economy/MD: https:// URL. MD frame mode requires first_image as well

reference_videos

string[]

Reference videos. Full: asset://{assetId}; Economy/MD: https:// URL. MD: max 3, combined duration ≤15s, combined size ≤200MB, each resolution 720px–2160px. Not supported on seedance2.0-fast-i2v

reference_audios

string[]

Reference audio. Supported on Full, SP economy, and STD. Not supported on MD or seedance2.0-fast-i2v. Full: asset://{assetId}; SP: https:// URL or asset://. STD max 3 clips; frame mode does not support audio references

Response

200 - application/json

Task created successfully

code

string

Example:

"20000"

msg

string

Example:

"ok"

data

object

Show child attributes

Query Asset Audit Status

Mini Special Create Video

​Models

​Billing

​Billable seconds

​Examples

​Request fields

​Assets

​Constraints

​Examples

​Mini — reference image

​Mini — first/last frame

​Mini video reference

​Response example

​Query task

Authorizations

Body

Response

Models

Billing

Billable seconds

Examples

Request fields

Assets

Constraints

Examples

Mini — reference image

Mini — first/last frame

Mini video reference

Response example

Query task