MiniMax modelsvideo generation api

minimax/h3/video-regeneration

Name: MiniMax H3 Video Regeneration
Author: MiniMax

Regenerate a single base video from a text prompt as a 2K MiniMax H3 video.

Input

Prompt(string)

The text instruction used to regenerate the base video.

Base Video(array)

Exactly one base video URL to regenerate.

Resolution(string)

Regeneration output resolution. MiniMax H3 regeneration supports 2K only. Allowed values: 2K.

AIGC Watermark(boolean)

Whether to add an AIGC label watermark to the regenerated video.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDminimax/h3/video-regeneration

Input Schema

4 parameters · 3 required · 1 optional

Parameter	Type	Required	Description
`prompt`	string	Required	The text instruction used to regenerate the base video. · Min length: 1
`videos`	string[]	Required	Exactly one base video URL to regenerate.
`resolution`	string	Required	Regeneration output resolution. MiniMax H3 regeneration supports 2K only. · Options: 2K · Default: "2K" 2K
`aigc_watermark`	boolean	Optional	Whether to add an AIGC label watermark to the regenerated video. · Default: false

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "minimax/h3/video-regeneration",
  "prompt": "Enhance the scene with cinematic lighting",
  "videos": [
    "https://static.sandbase.ai/examples/pixverse/sound-effects/input_video_0.mp4"
  ],
  "resolution": "2K",
  "aigc_watermark": false
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to MiniMax H3 Video Regeneration

API README

MiniMax H3 Video Regeneration

Regenerate one base video as a 2K MiniMax H3 video using a required text prompt. Upload exactly one video; SandBase securely assembles the request with the video as base_video.

Example request fields:

{
  "prompt": "Enhance the scene with cinematic lighting",
  "videos": ["https://static.sandbase.ai/examples/pixverse/sound-effects/input_video_0.mp4"],
  "resolution": "2K",
  "aigc_watermark": false
}

The $0.65 base price is a catalog reference for 5 output seconds with no chargeable input material. Final billing never falls back to the base price: it uses completed-task usage at $0.13 per output second and $0.08 per input-video second, plus $0.04 for each input image after the first 5. Reference audio is free. If any required usage value is unavailable or invalid, settlement remains pending for retry or reconciliation.