Cheaper Gen.
MiniMaxvideoUnavailable

MiniMax H3 Max API

The enhanced H3 for sharper detail and stronger prompt following

FromUp to −49%
$0.027/sOfficial price $0.05

per second of video · 480P

Try MiniMax H3 Max

Runs on your balance at the price shown on the button. Results are saved to your account.

Open full-screen Studio
0/5000

Output frame shape.

Output resolution. Higher resolutions cost more per second.

6s

Length of the generated clip in seconds (5–15s). You pay per second.

Estimated cost…

Create a free account with Google or email — pay only for what you generate.

Your video will appear here

Write a prompt, pick your settings and hit Run. You only pay for successful generations.

What is MiniMax H3 Max?

MiniMax H3 Max is the post-trained, higher-quality H3 with sharper detail and stronger prompt adherence, generating 480P and 768P videos of 5–15 seconds.

Sharper detail
Post-trained H3
480P / 768P
Fast-loading outputs
5–15 seconds
Pay per second
Frames
First & last frame control

H3, refined

H3 Max is post-trained on top of H3 for better prompt adherence, cleaner detail and more stable faces — a strong default for character-driven scenes.

MiniMax H3 Max pricing

Pay per second of video. No subscription. Failed generations are refunded automatically.

TierOfficial priceCheaper Gen.
480P
per second
$0.05/s$0.027/s
768P
per second
$0.08/s$0.041/s
  • Official price: MiniMax international official price ($0.05 / $0.08 per second). Prices verified 2026-10-14.

Specifications

Resolutions
480P · 768P
Duration
5–15 s
Aspect ratios
16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 21:9
Released
Sep 1, 2026

Use MiniMax H3 Max via API

One request to start a job, one to fetch the result. Same shape for every model.

Full API reference
import os, time, requests

API = "https://cheapergen.com/api/v1"
headers = {"Authorization": f"Bearer {os.environ['CHEAPERGEN_API_KEY']}"}

# 1. Submit the job
job = requests.post(f"{API}/run/minimax/h3-max/text-to-video", headers=headers, json={
    "prompt": "A hummingbird hovers at a red flower, wings frozen in a sliver of light, nature documentary",
    "aspect_ratio": "16:9",
    "resolution": "768P",
    "duration": 6
}).json()

# 2. Poll until it finishes (or pass "webhook_url" and skip polling)
while job["status"] in ("queued", "running"):
    time.sleep(3)
    job = requests.get(f"{API}/generations/{job['id']}", headers=headers).json()

print(job["status"], job["output"]["video"]["url"] if job["status"] == "succeeded" else job["error"])

Example prompts

Copy a prompt into the playground above to try it.

  • Close-up of an old fisherman laughing as rain begins, cinematic, 35mm film grain

    Try it

MiniMax H3 Max FAQ

MiniMax H3 Max is billed per second of output video at the selected resolution. In reference-to-video, reference-video seconds are billed at the same rate. Failed generations are never charged.

Yes — image-to-video accepts a first frame and an optional last frame, and the model animates between them.

Yes, subject to MiniMax's usage policy and our Terms of Service.

MiniMax H3 Max is developed by MiniMax. Cheaper Gen. provides API access through official upstream endpoints and does not own the model. Trademarks belong to their respective owners. · Markdown · OpenAPI