Skip to catalog
FbFable
CatalogLabsScoresCompare
Catalog
mm

MiniMax

MiniMax M3

minimax-m3

54Index
MiniMax Community · restrictedGenerally available1M contextTextImageAudioVideo

Pick this when

Cheap multimodal with a million-token window when the license fits.

Skip when

You need a permissive license or a proven coding-agent lead.

Quietly strong. Easy to miss because it does not buy launch-week headlines.

Price

Input / 1M
$0.30
Output / 1M
$1.20
Measured task
$0.22

Weights available. Community license restricts commercial use.

Shape

Context
1M
Max output
64K
Released
2026-07
Tools
Yes
Reasoning
Yes

Scores

Intelligence index54
GPQA Diamond85
Terminal-Bench 2.163
Agentic index35
Arena
—
Speed
120/s
GPQA
84.8%
Term.
63.2%
  • AA Index. The single number most people mean by “how smart.” It is a blend, so a specialist can lose here and still win the job you care about.
  • GPQA. A clean test of hard reasoning. PhD experts sit around 65%. It says little about writing, tools, or taste.
  • Term.. Closest public proxy for coding agents that live in a terminal. A high index score with a weak terminal score is a warning.
  • Arena. Captures taste and usefulness that unit tests miss. Sample size varies by model, so treat gaps under ~100 Elo as noise.

MiniMax · Shanghai. M3 is a cheap multimodal all-rounder with a million-token window. Weights exist. The community license restricts commercial use.

Compiled 2026-08-28 from public Artificial Analysis, LMSYS-style arena, and first-party price sheets. Scores move. Recheck before you spend.

A two-point gap on the intelligence index is noise for most work. Cost per finished task is the number that shows up on the invoice.