Create MiniMax H3 video

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>"
    }
  }
}

Asynchronously generate MiniMax H3 videos. Use the shared endpoint POST /v1/videos with one of the models below. On success you get a task_id; poll Query video task and read result.video_url when completed.

Models

`model`	Capabilities	Duration	Resolution
`minimax-h3`	Text-to-video; image / video / audio refs (max 9 total)	4–15 s	`720p` / `1080p`
`minimax-h3-max`	Same, Max tier	4–15 s	`720p` / `1080p`

Billing is per_second (cost = unit price × duration/seconds). See the model catalog and the cost field on create for live unit prices.

Mode

Mode	How to call
Text-to-video	Omit `images` / `videos` / `audios`, or pass empty arrays
Reference-driven	Provide at least one image, video, or audio reference

Describe each asset’s role and index in prompt (e.g. image 1, video 1, audio 1). First/last-frame fields are not supported.

Request fields

Field	Type	Required	Description
`model`	string	yes	`minimax-h3` or `minimax-h3-max`
`prompt`	string	yes	1–5000 characters
`duration` / `seconds`	int \| string	yes	4–15 (string form such as `"10"` is OK)
`aspect_ratio` / `ratio`	string	no	`16:9`, `9:16`, `1:1`, `4:3`, `3:4`, `21:9`; default `16:9`
`resolution`	string	no	`720p` (default) or `1080p`
`images` / `reference_images`	string[]	no	Reference image URLs
`videos` / `reference_videos`	string[]	no	Public video URLs
`audios` / `reference_audios`	string[]	no	Public audio URLs

Images, videos, and audios combined may total at most 9. References must be public https:// direct links.

Examples

Text-to-video

curl -X POST 'https://sigrunai.com/v1/videos' \
  -H 'Authorization: Bearer sk_xxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "minimax-h3-max",
    "prompt": "A cinematic night drive through neon rain in a future city",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 10
  }'

Single image reference

curl -X POST 'https://sigrunai.com/v1/videos' \
  -H 'Authorization: Bearer sk_xxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "minimax-h3",
    "prompt": "Use image 1 as the product hero for a clean spin showcase ad",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 8,
    "images": ["https://example.com/product.png"]
  }'

Image + video + audio

curl -X POST 'https://sigrunai.com/v1/videos' \
  -H 'Authorization: Bearer sk_xxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "minimax-h3",
    "prompt": "Image 1 for product look, video 1 for camera motion, audio 1 for edit rhythm",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 12,
    "images": ["https://example.com/ref.png"],
    "videos": ["https://example.com/ref.mp4"],
    "audios": ["https://example.com/ref.mp3"]
  }'

Response

Create returns the shared task payload (task_id, status, cost, …). When the job completes, poll 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, seedance2.0-md, sd2-480p-ac, sd2-720p-ac, seedance2.5-30s, or sd2.5-720p-ac

Example:

"omni-10s"

prompt

string

required

duration

omni-10s: fixed 10; seedance2.0-md: 5/10/15; sd2-*-ac: 4–15; seedance2.5-30s: fixed 30; sd2.5-720p-ac: 4–30

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

first_image

string<uri>

First-frame URL for omni-10s frame mode

last_image

string<uri>

Last-frame URL for omni-10s; use with first_image

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>[]

Response

200 - application/json

Submitted

code

integer

Example:

20000

msg

string

data

object

Show child attributes

Last modified on October 19, 2026

⌘I

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

MiniMax H3

Kling 4.0

Seedance 2.0

Seedance 2.5

Create MiniMax H3 video

Models

Mode

Request fields

Examples

Text-to-video

Single image reference

Image + video + audio

Response

Authorizations

Body

Response

​Models

​Mode

​Request fields

​Examples

​Text-to-video

​Single image reference

​Image + video + audio

​Response

Authorizations

Body

Response

Models

Mode

Request fields

Examples

Text-to-video

Single image reference

Image + video + audio

Response