MiniMax H3 Max API Quickstart

Send a video-generation request with model "Minimax/minimax-h3-max", a prompt, duration and resolution. Add an image URL for image-to-video.

Try MiniMax H3 Max in OneInfer Studio

Describe a scene or start from an image, and get a video. No code or API key; sign in with your OneInfer account.

Open in Studio(opens in a new tab)

Last verified 3 September 2026.

Use MiniMax H3 Max in 4 steps

Step 1 of 4

Try MiniMax H3 Max in the OneInfer playground without writing code, or create an API key in the Console to call it from your app.

export ONEINFER_API_KEY="your-api-key"

Minimal text-to-video request

Example
curl -X POST "https://api.oneinfer.ai/v1/ula/generate-video" \
  -H "Authorization: Bearer $ONEINFER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Minimax/minimax-h3-max",
    "prompt": "A cinematic tracking shot through a rain-lit night market",
    "resolution": "768P",
    "duration": 5,
    "aspect_ratio": "16:9"
  }'

Core parameters

FieldValue
modelMinimax/minimax-h3-max
promptRequired text prompt
duration5 to 15 seconds
resolution480P or 768P
aspect_ratioText-to-video only

Ready to test the workflow?

Do not send the upstream slug

The upstream fal slug is minimax/h3-max. When calling OneInfer, use Minimax/minimax-h3-max instead so catalog lookup, pricing and analytics resolve to the canonical model.

Frequently asked questions

What model ID should I use on OneInfer?

Use "Minimax/minimax-h3-max" exactly, including capitalization. The MiniMax provider model name is MiniMax-H3-Max, but that is not the OneInfer model ID.

How long can a MiniMax H3 Max video be?

H3 Max generates clips from 5 to 15 seconds at 24 fps.

Does MiniMax H3 Max generate audio?

Yes. It predicts synchronized audio alongside the video in the same generation.

Put MiniMax H3 Max to work

Fund a controlled evaluation, test it on your own inputs, and measure quality and cost on your workload.