ModelVideoClosed

MiniMax H3

MiniMax's newest video model family (2026), successor to Hailuo 02. It makes clips from a description, a photo, first and last frames, or reference images, video and audio, at up to 2K. Closed: use it in the Hailuo app or MiniMax's API, with cheaper Lite and Highspeed versions.

Go to MiniMax H3’s website

Free to try?No free plan

Can I sell what I make?The terms don't say clearly

Open or closedClosed

Skill neededNo setup

The facts, with sources

Open or closed: Closed
Only usable through the maker's app or API
API and app only.
source · checked 7 Nov 2026 · checked, but the page was unclear or partial
Licence: MiniMax API Platform Terms of Service (The maker's own terms)
Terms page exists but its text is rendered by script and could not be read.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Can I sell what I make?: The terms don't say clearly
API terms not readable (script-rendered). The consumer Hailuo app's terms describe personal, non-commercial use (see hailuo-ai entry).
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Cost: No free plan.
Plans below.
How you use it: Maker's own API, In your browser, Through another service
MiniMax API; Hailuo app; also on fal.
source · checked 7 Nov 2026 · checked, but the page was unclear or partial
Skill needed: No setup
Our judgement via the Hailuo app.
source · checked 7 Nov 2026 · checked, but the page was unclear or partial
Made by: MiniMax
Country not stated on the pages read; API terms page is rendered by script and could not be read.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
Priced on MiniMax's API as MiniMax-H3, -Highspeed, -Lite and -Max.
source · checked 7 Nov 2026 · checked on the maker's own page

What you can make with it

A video, from a description (main use)
A video, by bringing a photo to life
A video, lips that match new audio

text to videoimage to videovideo to videoaudio to video

t2v, i2v, first-and-last-frame and reference (image, video, audio). Lip-sync from fal's H3 Max lip-sync endpoint.

source · checked 7 Nov 2026 · checked, but the page was unclear or partial

Plans and prices

Plan	Price	Includes
API, H3 768p	$0.08 per seconds of video
API, H3 2K	$0.13 per seconds of video
API, H3 Lite 480p	$0.025 per seconds of video

Some plans are not listed here; see the source for the full list.

Per second of output. Highspeed $0.04-0.06/s; Max $0.05-0.08/s; first 5 input images per task free (2 for Max). Not in video packages yet.

source · checked 7 Nov 2026 · checked on the maker's own page

Rough cost of 5 seconds of 720p video: about $0.40 / £0.30 (estimate, worked out by Plainly, not a price the maker publishes). $0.08 per second x 5 at 768p = $0.40. GBP at 0.75 = 0.30.

Where you can run it

Hailuo AI, fal

Other options for “A video, from a description”

Adobe Express, Adobe Firefly, Adobe Premiere, Akool, Animoto, Arcads, Canva AI (Magic Studio), CapCut, Civitai, CogVideoX, ComfyUI, Creatify, DeeVid AI, DomoAI, Dreamina, Dzine, fal, Filmora, FlexClip, Fliki, FLORA, FLUX 3, Fotor, Gemini Omni 1.2 Flash

About this entry. Facts last checked 7 Nov 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.

Spot an error? Tell us, with a link to the source. How corrections work