MiniMax H3 Max API

minimax/h3-max
MiniMax H3 Max is a post-trained H3 video model tuned for faster generation and closer prompt adherence, producing 5-15 second clips at 480p or 768p and 24 fps with native stereo audio, from text, a first/last frame, or reference images, video and audio.
Output
$0.065/sec
Released
Aug 26, 2026

How to use MiniMax H3 Max API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to minimax/h3-max.

import requests, time

headers = {"Authorization": "Bearer " + AIMLAPI_KEY}
job = requests.post(
    "https://api.aimlapi.com/v2/video/generations",
    headers=headers,
    json={
      "model": "minimax/h3-max",
      "prompt": "A serene timelapse of clouds over a mountain range"
    },
).json()
gid = job["id"]

while True:
    res = requests.get(f"https://api.aimlapi.com/v2/video/generations?generation_id={gid}", headers=headers).json()
    if res.get("status") in ("completed", "error"):
      break
    time.sleep(5)
print(res["video"]["url"])

const headers = {
  Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
  "Content-Type": "application/json",
};
const job = await (await fetch("https://api.aimlapi.com/v2/video/generations", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "model": "minimax/h3-max",
    "prompt": "A serene timelapse of clouds over a mountain range"
  }),
})).json();

let res;
do {
  await new Promise((r) => setTimeout(r, 5000));
  res = await (await fetch(`https://api.aimlapi.com/v2/video/generations?generation_id=${job.id}`, { headers })).json();
} while (["completed", "error"].includes(res.status) === false);
console.log(res.video.url);

# submit the generation — the response contains the job "id"
curl -X POST https://api.aimlapi.com/v2/video/generations \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"minimax/h3-max","prompt":"A serene timelapse of clouds over a mountain range"}'

# then poll until status is "completed" — video.url holds the result
curl "https://api.aimlapi.com/v2/video/generations?generation_id={id}" -H "Authorization: Bearer $AIMLAPI_KEY"

OpenAI-compatible — swap the base URL and it works with your existing SDK.

MiniMax H3 Max API Pricing

TypePrice
Output
$0.065/sec

480p: $0.065/sec, 768p: $0.104/sec.

MiniMax H3 Max vs other models

ModelInputOutputContextBest for
$0.065/sec
Fast text-to-video and image-to-video generation
$0.169 / sec (2K)
Native 2K narrative video with synchronized audio and consistent characters
$0.559 / gen
Video generation
$0.559 / gen
Video generation

Frequently asked questions

MiniMax H3 Max takes audio, image, text, video as input and returns video.

MiniMax H3 Max became available on August 26, 2026.

MiniMax H3 Max is priced at $0.065/sec.

MiniMax H3 Max is billed per generation — a fixed charge per output rather than by prompt length.

Yes, MiniMax H3 Max accepts image input as well as a text prompt.

MiniMax H3 Max was built by MiniMax.

Send a request to https://api.aimlapi.com/v2/video/generations with minimax/h3-max as the model id.

Yes. MiniMax H3 Max is served through AI/ML API, so the same key and endpoint format used for other models applies.

No. It outputs video at 480p or 768p resolution, not 2K.

Yes, it supports reference-to-video generation, letting you feed reference images or video to maintain consistency.

The shortest clip is 5 seconds; clips can run up to 15 seconds.

It generates video at 24 frames per second.

Start building with MiniMax H3 Max

Get API Key
1000+ models, one API.