MiniMax h3 Lite

minimax-h3-lite

Generate 480p or 768P video with native audio from a single reference image using the MiniMax H3 Lite API. Upload a product photo or a photo from your menu and describe the movement, camera work, and sound for a 4–15 second clip. Draft animated menu clips, product previews, and social videos at 480p, then switch to 768P to review food textures and packaging details. Find video generation request examples, supported parameters, and usage pricing on the model page.

Published price
From $0.013 / second
Billing unit
/ second
Context / Max output
— / —
Listed routes
1
MODEL OVERVIEW

MiniMax h3 Lite

Generate 480p or 768P video with native audio from a single reference image using the MiniMax H3 Lite API. Upload a product photo or a photo from your menu and describe the movement, camera work, and sound for a 4–15 second clip. Draft animated menu clips, product previews, and social videos at 480p, then switch to 768P to review food textures and packaging details. Find video generation request examples, supported parameters, and usage pricing on the model page.

Overview for yir

MiniMax H3 Lite turns a single reference image into a short clip for a menu, product listing, or social post. On OpenAny, start at 480p to check the action and framing, then reuse the same prompt at 768P to examine textures, label text, and product edges. MiniMax H3 family overview · OpenAny route parameters

Example output

Still reference image of freshly baked scones

Watch the H3 Lite fresh scones demo ↗

Input

Action

Sample settings

A photo of scones and a brief that keeps the arrangement and warm kitchen light.

Steam rises, butter melts, and the camera slowly pushes in.

5 seconds, 480p

Cloudflare published the sample and used the photo as a first frame. The OpenAny request below uses it as a reference image and sets the output aspect ratio explicitly. Sample and original input

Choose your settings

Parameter

OpenAny template

Reference image

One public HTTPS image with the reference_image role.

duration

4–15 seconds. Start with four to six seconds for a small action.

resolution

480p or 768P. Use these exact values in the request.

aspect_ratio

21:9, 16:9, 4:3, 1:1, 3:4, or 9:16

generate_audio

Fixed at true.

n

Fixed at 1.

If the final clip will be vertical, use 9:16 for the draft too. Specify where the subject should sit and how much room to leave around it so you can check the crop.

Quickstart

In the OpenAny Playground, choose Reference image to video. To use the API, send a POST request to https://api.openany.si/v1/videos with the header Authorization: Bearer $OPENANY_API_KEY.

json
{
  "model": "minimax-h3-lite",
  "route": { "provider": "yir" },
  "route_mode": "balanced",
  "input": {
    "type": "reference",
    "prompt": "Use the reference photo to keep the scones and baking tray in the same arrangement. Add a thin trail of steam and a slow camera push toward the front scone. Keep the kitchen light warm and add a quiet room tone.",
    "references": [
      {
        "role": "reference_image",
        "url": "https://storage.googleapis.com/cloud-samples-data/generative-ai/image/scones.jpg"
      }
    ]
  },
  "parameters": {
    "duration": 5,
    "resolution": "480p",
    "aspect_ratio": "16:9",
    "generate_audio": true,
    "n": 1
  }
}

Poll GET /v1/videos/{task_id} and retrieve the video URL from the result's file list when the task succeeds. Check the steam, the shape of the scones, and the tray edges. To review finer textures, keep the prompt, duration, and aspect ratio fixed and change resolution to 768P.

Put the model to work.

Use Playground for a test, or inspect the API contract for your integration.

Model API questions

How do I call MiniMax h3 Lite through OpenAny?

Use model ID minimax-h3-lite with an OpenAny key and the operation published in this model's API tab. The model API base is https://api.openany.si/v1. Confirm the protocol and request schema; model availability does not imply every OpenAI API operation is supported.

How is MiniMax h3 Lite billed?

Compare the published rate and billing unit of the selected provider route. Input, output and cache token rates may differ. Image, audio and video models can use other units. Recorded usage determines the charge under that route's billing contract.

Are Community and Verified routes the same as an official publisher API?

No. Inspect the provider name and supply classification for the specific route. A marketplace listing or a supply label is not a claim of publisher endorsement, identical service or measured uptime. Different route prices may reflect different supply and conditions.

Where do these prices come from, and when were they updated?

Rates come from the provider routes in OpenAny's public model catalog, not an independent quote from the model publisher. The catalog does not supply a price update timestamp. A page or catalog snapshot date is not a price revision date. Compare supply, billing units, tiers and conditions; a lower listed rate alone does not establish equivalent service or explain the price difference.

Use MiniMax h3 Lite with your agent

Inspect endpoint contracts and confirm availability and pricing before a paid call.