opendunes

H3

by MiniMaxReleased 29 July 2026

MiniMax H3 edits and generates video from text, pictures, video and audio, with 2K output, built-in sound and clips of 5 to 15 seconds. It follows written edit instructions, shows text and logos legibly and copies motion from one video to another, which suits ads, product videos and game or app mockups. You can fix the first and last frames.

TakesTextImagesVideoAudio
GivesVideo
Open in chatCreate API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

43,27 DA per second of video3 000 DA buys 69 seconds of video

One second of video, the ordinary use

1 second of video× 43,27 DA43,27 DA
Total43,27 DA

Every rate

Meter↑ you send↓ comes back
Second of video43,27 DA

per second of video returned

↑ 13,31 DA per reference picture

A short product loop for a website≈ 216,35 DA
A short clip for a story post≈ 259,62 DA
An 8-second clip for a social post≈ 346,16 DA
Animate a shop photo into a short scene≈ 346,16 DA
A 15-second ad teaser≈ 649,05 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
The length, the sound and the resolution.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

One company runs this model. OpenDunes sends every request to it.

MinimaxUnited States…
Per second, with sound
43,27 DA
Latency
…
ProviderPer second, with soundLatencyUptime
MinimaxUnited States43,27 DA……

You pay the price of the provider that served your request. Prices read 15:19 · speed over the last 30 minutes · uptime over 3 days.

Call it in code

Send the job, then ask for it until it is ready.

POST /v1/videos · then GET /v1/videos/{id}
Base URL
https://opendunes.com/v1
Model ID
minimax/hailuo-3
import os, time, requests
BASE = "https://opendunes.com/v1"
KEY = os.environ["OPENDUNES_API_KEY"]
H = {"Authorization": f"Bearer {KEY}"}
job = requests.post(f"{BASE}/videos", headers=H, json={
    "model": "minimax/hailuo-3",
    "prompt": "Sunrise over the dunes of Taghit, slow pan",
    "duration": 8, "resolution": "2K",
    "generate_audio": False,
}).json()
while job["status"] not in ("completed", "failed"):
    time.sleep(10)
    job = requests.get(job["polling_url"], headers=H).json()
print(f"{BASE}/videos/{job['id']}/content")
pip install requestsFull reference for this route
Sign in to run it

Runs this request once on your balance.

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturetop_p

Questions about H3

  • How much does H3 cost in dinars?

    About 43,27 DA per second of video. ↑ 13,31 DA per reference picture.

  • Is H3 free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is H3 best for?

    MiniMax H3 edits and generates video from text, pictures, video and audio, with 2K output, built-in sound and clips of 5 to 15 seconds. It follows written edit instructions, shows text and logos legibly and copies motion from one video to another, which suits ads, product videos and game or app mockups. You can fix the first and last frames.

  • H3 or H3 Max?

    H3 Max costs 16,64 DA less for the same second of video.

  • How do I pay for H3 without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, H3 included, is paid from that balance. No foreign card, no conversion.

  • Does H3 work in Arabic, French or Darja?

    MiniMax lists stable dialogue support for Arabic, Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian and Spanish. Darja is not named.

  • How long can a clip be, and does it make sound?

    5 to 15 seconds. With sound.

  • Can it animate my photo, or make a vertical video?

    From a first and a last frame. Vertical 9:16: yes.

  • Who makes H3, and when was it released?

    MiniMax. Released 29 July 2026.

Other MiniMax models, priced in dinars

See all MiniMax models
MiniMax M3.1 FlashMiniMax · Oct 19, 2026

This model accepts text, pictures, and video inputs, and can process up to 1000 pages of information to generate responses up to 520 pages long. It excels at complex tasks like coding, cybersecurity, and advanced problem-solving. Its ability to handle video input and its high ranking in reasoning set it apart from other models. However, it cannot search the web or structure data into specific formats.

Thinks firstUses your tools1 000 pages at once
≈0,15 DAper message
View model
Speech 2.8 HDMiniMax · Jul 16, 2026

MiniMax Speech 2.8 HD turns text into speech and returns audio, using any MiniMax voice you name. It is the quality tier: it voices laughs and sighs written into the text as tags, and it supports emotion settings like happy, sad or calm. Use it for narration, audiobooks and finished voice-overs.

45 voices
≈19,97 DAper paragraph read aloud
View model
Hailuo 2.3MiniMax · Apr 20, 2026

MiniMax's Hailuo 2.3, aimed at cinematic scenes and character animation where motion must look real and characters expressive, producing 6 or 10 second 1080p clips from a prompt or an opening image

Animates your photoUp to 10 s1080p
27,19 DAper second of video
View model
H3 MaxMiniMax · Sep 2, 2026

MiniMax H3 Max makes video from a written description or a picture at a lower resolution than H3, in clips of 5 to 15 seconds, and lets you fix the first frame, the last frame or both. It is the faster model, built on MiniMax H3 with extra training, so it suits drafts and quick tries on a shot. Its output is silent.

Animates your photoFirst + last frameUp to 15 s
26,63 DAper second of video
View model