opendunes

MiniMax M3 (batch)

by MiniMaxReleased 31 May 2026

MiniMax M3 takes text, pictures and video and answers in text, keeping about a thousand pages in mind and writing up to about 512 pages in one reply. It is made for long-running automated tasks, coding and tool use, and is tuned for back-and-forth collaboration rather than single answers. It stays efficient on very long inputs.

TakesTextImagesVideo
GivesText
Create API keyCompare

What it costs

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

≈ 0,22 DA per message3 000 DA buys about 13 000 messages

One message, the ordinary use

1 000 tokens sent× 74,56 DA per 1M0,075 DA
500 tokens back× 292,90 DA per 1M0,15 DA
Total≈ 0,22 DA

Every rate

Meter↑ you send↓ comes back
Text tokens74,56 DA292,90 DA
Cached tokens read14,91 DA

per 1M tokens

When you pay
After the answer, from your balance. Nothing is held.
Why it varies
A longer question or a longer answer costs more.
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. DA per 1M tokens: ↑ what you send · ↓ what comes back.

DeepInfraUnited States…
↑ Sent, per 1M
74,56 DA
↓ Back, per 1M
292,90 DA
Cache read
14,91 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
DeepInfraUnited States74,56 DA292,90 DA14,91 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

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions
Base URL
https://opendunes.com/v1
Model ID
minimax/minimax-m3:batch
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.chat.completions.create(
    model="minimax/minimax-m3:batch",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)
pip install openaiFull 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_ptop_kmin_pstopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_bias

Reasoning

Let it think before answering — and see the thinking.

reasoninginclude_reasoning

Structured output

Get JSON you can parse instead of prose.

response_format

Tools

Let the model call your functions.

toolstool_choice

Questions about MiniMax M3 (batch)

  • How much does MiniMax M3 (batch) cost in dinars?

    About 0,22 DA per message. ↑ 74,56 DA · ↓ 292,90 DA per 1M tokens.

  • Is MiniMax M3 (batch) free? Can I try it?

    No. You pay per use from your balance, with no subscription. Run it once from Call it in code, at the same price.

  • What is MiniMax M3 (batch) best for?

    MiniMax M3 takes text, pictures and video and answers in text, keeping about a thousand pages in mind and writing up to about 512 pages in one reply. It is made for long-running automated tasks, coding and tool use, and is tuned for back-and-forth collaboration rather than single answers. It stays efficient on very long inputs.

  • How do I pay for MiniMax M3 (batch) without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, MiniMax M3 (batch) included, is paid from that balance. No foreign card, no conversion.

  • Does MiniMax M3 (batch) work in Arabic, French or Darja?

    MiniMax names no languages for MiniMax M3 (batch). Arabic, French and Darja: not stated.

  • Can it read PDFs, images or a whole book?

    It reads text, images and video. Up to 524K tokens in one request, about 520 pages. It writes up to 384 000 words at once.

  • Is MiniMax M3 (batch) open source?

    Yes, its weights are public. Open weights on Hugging Face

  • Who makes MiniMax M3 (batch), and when was it released?

    MiniMax. Released 31 May 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
H3MiniMax · Jul 29, 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.

Makes soundAnimates your photoFirst + last frame
43,27 DAper second of video
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