Skip to content
trckr.ai

Loading…

Learn · Compare

Compare two models.

Side by side

Swap
MiniMax

MiniMax-M2.5

Release page →
MiniMax

MiniMax-M2.1

Release page →

The basics

Released

Feb 12
Dec 23, 2025

What it does

Text and chat: Writes, answers questions and holds a conversation.Code: Writes, explains and fixes code.Thinks first: Can reason step by step before it answers: slower, but better at maths, code and tricky questions.
Text and chat: Writes, answers questions and holds a conversation.Code: Writes, explains and fixes code.Thinks first: Can reason step by step before it answers: slower, but better at maths, code and tricky questions.

Knowledge cutoff

The latest events it learned about

Not published
Not published

Download

FreeOpen weights
FreeOpen weights

Where to use it

MiniMax's app: MiniMax Agent ↗
MiniMax's app: MiniMax Agent ↗

Price and limits, for developers

Input

Per million tokens

$0.30
$0.30

Output

Per million tokens

$1.20
$1.20

Cached input

Per million tokens

$0.03
$0.03

Context window

How much it takes in at once

205K tokens about 150,000 words
205K tokens about 150,000 words

Longest answer

59K tokens about 44,000 words
Not listed

How they score

Neither model is in the public rankings trckr follows yet. New models usually appear within a few weeks of launch.

Green marks the better of the two on each row, red the other. Rows where one side isn't listed, or where the gap is too close to call, stay plain.

Popular comparisons

Not sure where to start? Which AI should I use? gives a pick for what you want to do. How to read AI rankings explains the numbers.

Rankings from LMArena and Epoch AI, both CC BY 4.0, updated . Developer prices, context windows and knowledge cutoffs from the labs' own listings on models.dev and from OpenRouter. The app links go to each maker's own app when no source says exactly where the model is available.

Free alerts

Know the moment a new model drops.

Pick one or several. Each has its own settings for what you hear about.