MiniMax

MiniMax M3

Type
language model
Context
1,049K tokens
Max output
512K
Released
12 June 2026
API string
accounts/fireworks/models/minimax-m3
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
EmpirioLabs AI $0.225 $0.9 31 Jul 2026
Weights & Biases $0.23 $0.96 31 Jul 2026
lilac $0.28 $1.1 31 Jul 2026
opencode-go $0.3 $1.2 31 Jul 2026
cline-pass $0.3 $1.2 31 Jul 2026
minimax-cn $0.3 $1.2 31 Jul 2026
Abacus.AI $0.3 $1.2 31 Jul 2026
DeepInfra $0.3 $1.2 31 Jul 2026
Fireworks AI $0.3 $1.2 31 Jul 2026
Hugging Face $0.3 $1.2 31 Jul 2026
Kilo Code $0.3 $1.2 31 Jul 2026
LLM Gateway $0.3 $1.2 31 Jul 2026
Merge Gateway $0.3 $1.2 31 Jul 2026
MiniMax $0.3 $1.2 31 Jul 2026
NanoGPT $0.3 $1.2 31 Jul 2026
Nebius Token Factory $0.3 $1.2 31 Jul 2026
OpenCode Zen $0.3 $1.2 31 Jul 2026
OpenRouter $0.3 $1.2 31 Jul 2026
Pioneer $0.3 $1.2 31 Jul 2026
Together AI $0.3 $1.2 31 Jul 2026
Vercel $0.3 $1.2 31 Jul 2026
hyper $0.327 $1.307 31 Jul 2026
wafer.ai $0.33 $1.32 31 Jul 2026
CrossModel $0.33 $1.32 31 Jul 2026
Cortecs $0.355 $1.775 31 Jul 2026
tensorx $0.4 $2 2 Aug 2026
synthetic $0.6 $1.2 31 Jul 2026
ZenMux $0.6 $2.4 31 Jul 2026

Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.

The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.

Measurement results

Task set Result Run conditions Measured by
Arena Score, web development 1,490.74 1,483–1,499
Arena Score, programming 1,472.57 1,465–1,480
Arena Score, expert questions 1,468.91 1,458–1,480
Arena Score in English 1,449.67 1,443–1,456
Arena Score, hard prompts 1,449.05 1,443–1,455
Arena Score, long queries 1,445.47 1,439–1,452
Arena Score, multi-turn dialogue 1,443.12 1,434–1,452
Arena Score, mathematics 1,442.28 1,426–1,458
Arena Score in French 1,441.49 1,422–1,461
Arena Score, overall 1,435.95 1,431–1,441
Arena Score, instruction following 1,434.31 1,427–1,442
Arena Score in Russian 1,430.47 1,419–1,441
Arena Score in Spanish 1,428.58 1,407–1,450
Arena Score, creative writing 1,403.76 1,394–1,413
Arena Score, understanding diagrams 1,269.29 1,257–1,282
Arena Score, text recognition in images 1,267.66 1,259–1,276
Arena Score, working with images 1,258.26 1,250–1,267
SimpleBench — trick questions 34.96 % SimpleBench Leaderboard
FrontierCode — patches fit to be merged into a project 14.7 % https://cognition.com/frontiercode
OSWorld 2.0 — working inside an operating system 4.6 % https://osworld-v2.xlang.ai/ self-reported
CritPt — physics problems 3.71 %
Arena Score, agent tasks -0.03 0–0