MiniMax H3 Max

POST Base URL: https://api.hiapi.ai /v1/tasks

Image, video, and audio models are called through the Unified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name	minimax-h3-max
Type	Text-to-video and image-to-video
Endpoint	POST /v1/tasks
Pricing	View live pricing

Generate videos from text, or use images to guide the opening and ending frames. Supports 480P and 768P output with a duration of 5–15 seconds.

Production guidance

Use callback.url for terminal notifications and deduplicate by taskId.
Keep polling tasks that are still processing; avoid duplicate submissions.

Best suited for

Generate a video from text

Describe the scene, action, and camera movement to generate a video.

Animate an image

Set an image as the opening frame and describe movement in the prompt. You can also guide the ending with an image.

Request parameters

POST https://api.hiapi.ai/v1/tasks

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax-h3-max",
  "input": {
    "prompt": "After a morning rain, a red paper boat drifts through shallow water beneath a stone bridge. A low camera tracks smoothly beside it, small ripples spread across the water, and birds sing softly in the distance. No text or subtitles.",
    "duration": 5,
    "resolution": "768P",
    "aspect_ratio": "16:9"
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "minimax-h3-max",
  "input": {
    "prompt": "After a morning rain, a red paper boat drifts through shallow water beneath a stone bridge. A low camera tracks smoothly beside it, small ripples spread across the water, and birds sing softly in the distance. No text or subtitles.",
    "duration": 5,
    "resolution": "768P",
    "aspect_ratio": "16:9"
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "minimax-h3-max",
  "input": {
    "prompt": "After a morning rain, a red paper boat drifts through shallow water beneath a stone bridge. A low camera tracks smoothly beside it, small ripples spread across the water, and birds sing softly in the distance. No text or subtitles.",
    "duration": 5,
    "resolution": "768P",
    "aspect_ratio": "16:9"
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Use minimax-h3-max.

example minimax-h3-max

input object required

Video generation parameters.

prompt string required

Describe the scene, character actions, camera movement, and sound, using up to 7,000 characters.

duration integer optional

Length of the generated video, from 5 to 15 whole seconds.

default 5

resolution enum optional

Resolution of the generated video.

default 768P enum: 480P768P

aspect_ratio enum optional

Width-to-height ratio of the generated video. When a first or last frame is supplied, the image determines the ratio.

default 16:9 enum: 21:916:94:31:13:49:16

first_frame_image string optional

The image to use as the first frame of the video.

last_frame_image string optional

The image to use as the last frame of the video.

callback object optional

Callback configuration for terminal task notifications.

url string required

HTTPS URL that receives task notifications.

example https://your-domain.com/hiapi/callback

when enum optional

Notify when the task reaches a terminal state.

default final enum: final

Example requests

Text-to-video

Describe a paper boat drifting after the rain to generate a landscape video.

Request body

{
  "model": "minimax-h3-max",
  "input": {
    "prompt": "After a morning rain, a red paper boat drifts through shallow water beneath a stone bridge. A low camera tracks smoothly beside it, small ripples spread across the water, and birds sing softly in the distance. No text or subtitles.",
    "duration": 5,
    "resolution": "768P",
    "aspect_ratio": "16:9"
  }
}

Guide the ending with an image

Supply a last-frame image URL to guide the final composition.

Request body

{
  "model": "minimax-h3-max",
  "input": {
    "prompt": "The camera slowly pushes forward and ends in the supplied last-frame composition.",
    "duration": 5,
    "resolution": "768P",
    "last_frame_image": "https://example.com/end.jpg"
  }
}

Getting the result

Authenticate with Authorization: Bearer YOUR_HIAPI_API_KEY and save the returned taskId.
Poll GET /v1/tasks/{taskId}, or set callback.url to receive a terminal notification.
Keep polling queued or processing tasks without submitting duplicates. On success, read the video URL from output[].url.
Handle failures using the returned error. Deduplicate callbacks by taskId.

FAQ

How do I generate landscape or portrait videos?

For text-only generation, choose aspect_ratio, such as 16:9 for landscape or 9:16 for portrait. When using frame images, prepare images with the ratio you want; the image determines the video ratio.

Can I supply reference videos, reference audio, or other controls?

This API does not accept reference videos, reference audio, mode, watermark, or seed. Use the fields listed in the parameter table.