Create a Wan 3 video

统一视频创建入口。当前可用 model：omni-10s、veo3.1-fast、veo3.1-lite、veo3.1-lite-hd、grok-imagine-video-1.5（及 fast/lite）、minimax-h3、minimax-h3-max、kling-4.0（720p/1080p）、sd2.5-480p / sd2.5-720p / sd2.5-1080p（按秒）、seedance2.0-md、sd2-480p-ac、sd2-720p-ac、sd2-720p-dl、sd2-720p-db、sd2.0-mini-720p、seedance2.5-30s、sd2.5-720p-ac、sd2.5-720p-933-ac、wan3-720p / wan3-1080p（按秒）、wan3.0-prime-720p / wan3.0-prime-1080p（按秒）、wan3-480p-20s-ac、muse-video / muse-video-20s / muse-video-30s / muse-video-40s / muse-video-50s / muse-video-60s（1–60 秒，按时长分档，原生 720p，按次）。Veo 也可用专用入口 POST /v1/veo/frames。

POST

videos

curl --request POST \
  --url https://sigrunai.com/v1/videos \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "omni-10s",
  "prompt": "A golden retriever running across a sunny meadow, cinematic tracking shot",
  "aspect_ratio": "16:9"
}
'

{
  "code": 20000,
  "msg": "<string>",
  "data": {
    "task_id": "<string>",
    "status": "<string>",
    "progress": 123,
    "model": "<string>",
    "created_at": 123,
    "completed_at": 123,
    "cost": 123,
    "error_message": "<string>",
    "result": {
      "image_url": "<string>",
      "video_url": "<string>"
    }
  }
}

Create a Wan 3 video asynchronously. Use POST /v1/videos with a billing key: wan3-720p or wan3-1080p. On success you get a task_id. Poll Query video task and read result.video_url when the task completes.

Models

`model`	Notes	Duration	Resolution
`wan3-720p`	Billing key: 720p	10–30 seconds	`720p`
`wan3-1080p`	Billing key: 1080p	10–30 seconds	`1080p`

Billing mode is per_second. Cost = the resolution unit price × requested seconds. Live prices come from the model catalog and the cost field on the response. model: "wan3" is also accepted. Set resolution to pick the tier (default 720p). The task model is stored as the billing key.

Modes

Mode	How to call
Text to video	Omit `images` / `videos` / `audios`, or send empty arrays
Reference generation	Pass reference images, videos, and/or audio

First and last frames are not supported.

Reference limits

Type	Maximum
Images	9
Videos	3
Audio	3

Reference files must be public URLs.

Request fields

Field	Type	Required	Notes
`model`	string	yes	`wan3-720p` / `wan3-1080p`. `wan3` plus `resolution` also works
`prompt`	string	yes	1–10000 characters
`duration` / `seconds`	int \| string	no	10–30. Defaults to 10. Strings such as `"15"` are accepted
`aspect_ratio` / `ratio`	string	no	`16:9`, `9:16`, `4:3`, `3:4`, `1:1`. Default `16:9`
`resolution`	string	no	`720p` or `1080p`. When the billing key already includes a resolution, omit this or send the same value
`images` / `reference_images`	string[]	no	Up to 9 image URLs
`videos` / `reference_videos`	string[]	no	Up to 3 video URLs
`audios` / `reference_audios`	string[]	no	Up to 3 audio URLs
`smart_queue`	bool	no	Default `false`. When `true`, a model with a low recent success rate stays `queued` until it recovers (about 2 hours at most). See Smart queue

Examples

Text to video

curl -X POST 'https://sigrunai.com/v1/videos' \
  -H 'Authorization: Bearer sk_xxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "wan3-720p",
    "prompt": "A rainy neon street, camera pushing slowly forward",
    "aspect_ratio": "16:9",
    "duration": 10
  }'

1080p with a reference image

curl -X POST 'https://sigrunai.com/v1/videos' \
  -H 'Authorization: Bearer sk_xxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "wan3-1080p",
    "prompt": "The person in the reference image walks down a rainy street",
    "aspect_ratio": "9:16",
    "duration": 15,
    "images": ["https://example.com/person.jpg"]
  }'

Response

Create returns the shared task payload (task_id, status, cost, …). data.model is the billing key (for example wan3-720p). Poll the query endpoint for result.video_url.

Authorizations

Authorization

string

header

required

控制台创建的 API Key，格式：Bearer sk_xxx

Body

application/json

model

string

required

omni-10s, veo3.1-fast, veo3.1-lite, veo3.1-lite-hd, grok-imagine-video-1.5 (and fast/lite), minimax-h3, minimax-h3-max, kling-4.0 / kling-4.0-720p / kling-4.0-1080p, sd2.5-480p / sd2.5-720p / sd2.5-1080p, seedance2.0-md, sd2-480p-ac, sd2-720p-ac, sd2-720p-dl, sd2-720p-db, sd2.0-mini-720p, seedance2.5-30s, sd2.5-720p-ac, sd2.5-720p-933-ac, wan3-720p / wan3-1080p, wan3.0-prime-720p / wan3.0-prime-1080p, wan3-480p-20s-ac, or muse-video / muse-video-20s / muse-video-30s / muse-video-40s / muse-video-50s / muse-video-60s

Example:

"omni-10s"

prompt

string

required

duration

omni-10s: fixed 10; seedance2.0-md: 5/10/15; sd2-*-ac: 4–15; sd2-720p-dl: fixed 15; sd2-720p-db: 5/10/15; sd2.0-mini-720p: 4–15; sd2.5-480p / sd2.5-720p / sd2.5-1080p: 5–30; seedance2.5-30s: fixed 30; sd2.5-720p-ac and sd2.5-720p-933-ac: 4–30; wan3-720p / wan3-1080p: 10–30; wan3.0-prime-720p: 10–30; wan3.0-prime-1080p: 8–30; wan3-480p-20s-ac: 5–20; Muse Video: 1–60, billed as muse-video (1–10, default 5s when omitted) or muse-video-20s through muse-video-60s

seconds

Alias of duration

aspect_ratio

string

ratio

string

Alias of aspect_ratio

orientation

string

portrait/landscape may imply aspect ratio

size

string

resolution

string

omni-10s is fixed at 720p. Muse Video supports 720p only

first_image

string<uri>

First-frame URL. Used by omni-10s and Muse Video

last_image

string<uri>

Last-frame URL; use with first_image. Muse Video also requires a first frame

images

string<uri>[]

reference_images

string<uri>[]

videos

string<uri>[]

reference_videos

string<uri>[]

reference_video_durations

integer[]

Required with reference videos for kling-4.0; same length as videos; seconds 1–30. Billable seconds = output duration + sum of these values.

Required range: 1 <= x <= 30

reference_audio_durations

integer[]

Required with reference audios for kling-4.0; same length as audios; seconds 5–30 (validation only, not billed).

Required range: 5 <= x <= 30

audios

string<uri>[]

reference_audios

string<uri>[]

first_image_url

string<uri>

Alias of first_image. Accepted by Muse Video

last_image_url

string<uri>

Alias of last_image. Muse Video requires a first frame as well

image_urls

string<uri>[]

Reference image URLs. Muse Video: frames plus references, up to 10 on the 10s tier and 9 on the 20–60s tiers

reference_image_urls

string<uri>[]

Alias of images

camera_movement

string

Muse Video camera move, free text, up to 1000 characters

style

string

Muse Video style, free text, up to 1000 characters

negative_prompt

string

Muse Video negative prompt, separate from prompt, up to 1000 characters

smart_queue

boolean

default:false

When true, a very low recent success rate keeps the task queued until recovery (up to about 2 hours)

Response

200 - application/json

Submitted

code

integer

Example:

20000

msg

string

data

object

Show child attributes

Last modified on November 8, 2026

curl --request POST \
  --url https://sigrunai.com/v1/videos \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "omni-10s",
  "prompt": "A golden retriever running across a sunny meadow, cinematic tracking shot",
  "aspect_ratio": "16:9"
}
'

{
  "code": 20000,
  "msg": "<string>",
  "data": {
    "task_id": "<string>",
    "status": "<string>",
    "progress": 123,
    "model": "<string>",
    "created_at": 123,
    "completed_at": 123,
    "cost": 123,
    "error_message": "<string>",
    "result": {
      "image_url": "<string>",
      "video_url": "<string>"
    }
  }
}

Gemini Omni

Veo 3.1

Grok Imagine Video

Muse Video

MiniMax H3

Kling 4.0

Wan 3

Seedance 2.0

Seedance 2.5

Create a Wan 3 video

Models

Modes

Reference limits

Request fields

Examples

Text to video

1080p with a reference image

Response

Authorizations

Body

Response