We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.

MiniMax: H3 Max

minimax/hailuo-3-max
VideoInput: text · imageAdded Sep 2, 2026

Try MiniMax: H3 Max now

Runs on your balance at the prices above. New accounts start with free usage.

Sign in to use thisCreate free account
Results will appear here.
5 of 5 free messages left today. A free account adds free usage and an API key.Create free accountSign inSession cost $0.00

About MiniMax: H3 Max

MiniMax: H3 Max is a video generation model from MiniMax, released jointly with fal.ai. It sits in the video category and is derived through additional training from MiniMax H3. It is designed for faster text-to-video and image-to-video generation, which makes it a fit for workflows where turning a written prompt or a still image into a moving clip is the core task.

The model accepts text and image inputs and produces video as its only output. It supports two frame image options, first_frame and last_frame, so you can anchor a clip at its start, its end, or both. Output resolutions are 768p and 480p, and clips can run from 5 to 15 seconds in one-second steps. Aspect ratios cover 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, and 9:16, so both wide and vertical formats are available. Audio generation is not supported, so clips are silent and any sound must be added separately. No context length is listed for this model.

Practical uses follow from the input and output shape. Text-to-video suits storyboards, concept previews, and short social clips built from a prompt alone. Image-to-video suits animating a still, and the frame image options let you control where a shot begins or lands, which is useful for shot-to-shot continuity or for matching an existing edit. The range of aspect ratios covers widescreen delivery and vertical formats for mobile feeds, and the 5 to 15 second durations fit short-form content rather than long sequences.

You call H3 Max through api14's OpenAI-compatible API using the model id "minimax/hailuo-3-max". The supported request parameters are max_tokens, temperature, and top_p. Because the API is OpenAI-compatible, existing clients and SDKs that already point at api14 should work with this model id and these parameters without a separate integration.

If your task is audio and video together, H3 Max is not the right choice since generateAudio is false. If you need clips longer than 15 seconds or resolutions above 768p, this model does not offer them, and a different video model may fit better. If your work is text or image output rather than video, a text or image model is the more direct option.

How to call the MiniMax: H3 Max API

  1. Create an API key in your dashboard.
  2. Install the official openai SDK for your language.
  3. Set baseURL to https://api14.com/api/v1 and model to "minimax/hailuo-3-max".
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api14.com/api/v1",
  apiKey: process.env.API14_API_KEY,
});

// Video generation is asynchronous: submit, then poll until completed.
let job = await client.post("/videos", { body: {
  "model": "minimax/hailuo-3-max",
  "prompt": "A drone shot over turquoise ocean waves at sunrise",
  "duration": 8,
  "resolution": "720p",
  "aspect_ratio": "16:9"
} });
while (!["completed", "failed"].includes(job.status)) {
  await new Promise((r) => setTimeout(r, 5000));
  job = await client.get(`/videos/${job.id}`);
}
console.log(job.status, job.unsigned_urls);

Supported parameters

max_tokenstemperaturetop_p

Specifications

Input
text, image
Output
video
Resolutions
768p, 480p
Durations
5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s
Aspect ratios
21:9, 16:9, 4:3, 1:1, 3:4, 9:16

Requests on api14 · last 7 days

10-1610-1710-1810-1910-2010-2110-22

MiniMax: H3 Max: frequently asked questions

How much does the MiniMax: H3 Max API cost?
MiniMax: H3 Max costs duration_seconds $0.28 / second. It is charged from your USD balance only for successful requests; failed requests are free.
What can MiniMax: H3 Max do?
MiniMax: H3 Max accepts text, image and returns video.
How do I call MiniMax: H3 Max from my code?
Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "minimax/hailuo-3-max". No other code changes. Copy a ready example from the code panel on this page.
What are alternatives to MiniMax: H3 Max?
Comparable Video models at a similar price: Google: Veo 3.1 Lite, Alibaba: Wan 2.6, HeyGen: HeyGen Video. Each runs through the same API key, so switching is one string.

MiniMax: H3 Max community

New topic

This community has no topics yet. Open the first one about MiniMax: H3 Max.