minimax-m2.5

1390 Score third-party Elo · arena.ai / LMArena ?

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

LLM & Generative AI 1 model 4 listings snapshot Oct 14, 2026, 12:54 AM

Platforms

click a card to open the detail table

Cheapest OpenRouter no official benchmark Input$0.270 Output$1.08 per 1M tokens Fastest OpenRouter lowest p50 latency on this board 128.1 ms p50 Most free quota — largest published free allowance — free tier

Model variants

W3r9 dedup — same model + identical tags merge; prices are listed per billing form

Model	Provider	Tags	Input /1M	Output /1M
minimax/minimax-m2.5	OpenRouter	200k contextreasoning	$0.270	$1.08
MiniMax/MiniMax-M2.5	DashScope	200k contextreasoning	$0.311	$1.24
MiniMax-M2.5	DashScope	200k contextreasoning	$0.311	$1.24
minimax/minimax-m2.5	Novita	200k contextreasoning	$0.300	$1.20

Capabilities

official design_arena & architecture metadata

Design Arena Elo official design_arena benchmark (OpenRouter)

website 1225 · 57.5% wr
codecategories 1210 · 56.8% wr
gamedev 1181 · 55.5% wr
uicomponent 1174 · 53.4% wr
dataviz 1173 · 51.2% wr
3d 1171 · 57.6% wr
svg 1149 · 54.5% wr

Input / Output modalities modality: text->text

text in+out

Platform details

per provider

provider	model	Input /1M	Output /1M	Latency ?	Official $/1M	Availability	Data time
DashScope	MiniMax-M2.5	$0.311	$1.24	—	—	—	2026-10-14 00:53:13
Novita	minimax/minimax-m2.5	$0.300	$1.20	—	—	—	2026-10-14 00:54:15
OpenRouter	minimax/minimax-m2.5	$0.270	$1.08	128.1 ms	—	100% available	2026-10-14 00:43:21
Together	MiniMaxAI/MiniMax-M2.5-FP4	$0	$0	—	—	—	2026-10-14 00:53:13

4 rows · snapshot 2026-10-14 00:54:15 · from data/public/prices.json + measurements.json