modelbenchmark.io

MiniMax-M2.5

MiniMax · minimax-m2-5

Compare

Prior MiniMax coding model for agent workflows, office edits, and automation

Specification

minimax listing

Context
205K
Max output
131K
Released
2026-02-12
Knowledge cutoff
2025-08
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · minimax list price

Input
$0.30
Output
$1.20
Cache read
$0.03
Cache write
$0.375

Quality

1 benchmark · 1 source

Composite
91st
percentile of 334 scored models
Rank
32 / 334
±0.10 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
one configuration only
coding84th1/3 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
SWE-Bench verified75.8high · mini-SWE-agentSWE-bench

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 54 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
minimaxvendor$0.30$1.20$0.03$0.375205K131K
alibaba-coding-planfreefreefreefree197K25K
alibaba-coding-plan-cnfreefreefreefree197K25K
alibaba-token-planfreefreefreefree197K33K
alibaba-token-plan-cnfreefreefreefree197K33K
minimax-cn-coding-planfreefreefreefree205K131K
minimax-coding-planfreefreefreefree205K131K
scnet-token-planfreefreefree205K131K
tencent-coding-planfreefreefreefree205K33K
deepinfra · minimaxai$0.15$1.15$0.03197K131K
greenpt$0.1938$1.129$0.0627205K131K
dinference$0.22$0.88200K32K
openrouter$0.27$1.08$0.027197K66K
openrouter · minimax$0.27$1.08$0.027205K128K
cortecs$0.296$1.186$0.075196K196K
302ai$0.30$1.20205K131K
alibaba-cn$0.30$1.20205K131K
baseten$0.30$1.20
baseten · minimaxai$0.30$1.20204K204K
cloudferro-sherlock · minimaxai$0.30$1.20196K16K
digitalocean$0.30$1.20$0.0666K66K
edenai · minimax$0.30$1.20$0.03205K131K
friendli · minimaxai$0.30$1.20$0.06197K131K
friendliai · friendliai$0.30$1.20$0.06197K197K
frogbot$0.30$1.20$0.03192K8K
hpc-ai · minimax$0.30$1.20$0.03196K195K
huggingface · minimaxai$0.30$1.20$0.03205K131K
kilo · minimax$0.30$1.20$0.03200K128K
llmgateway$0.30$1.20$0.03$0.375229K131K
llmgateway-providers$0.30$1.20$0.03205K131K
llmgateway-providers · minimax$0.30$1.20$0.03205K131K
meganova · minimaxai$0.30$1.20205K131K
merge-gateway · minimax$0.30$1.20$0.03$0.375205K8K
minimax · minimax$0.30$1.20$0.03$0.3751M8K
minimax-cn$0.30$1.20$0.03$0.375205K131K
nano-gpt · minimax$0.30$1.20$0.15205K131K
nebius$0.30$1.20197K197K
novita$0.30$1.20$0.03205K131K
novita-ai · minimax$0.30$1.20$0.03205K131K
ofox · minimax$0.30$1.20$0.03$0.375205K131K
opencode$0.30$1.20$0.06205K131K
opencode-go$0.30$1.20$0.03205K66K
orcarouter · minimax$0.30$1.20$0.03$0.375205K131K
siliconflow · minimaxai$0.30$1.20$0.03197K131K
siliconflow-cn · pro$0.30$1.22192K131K
tensormesh · tensormesh$0.30$1.20free197K197K
tensorx · minimax$0.30$1.20$0.075$0.375197K66K
togetherai · minimaxai$0.30$1.20$0.06205K131K
tokengo · minimax$0.30$1.20$0.03205K131K
vercel · minimax$0.30$1.20$0.03$0.375205K131K
wandb · wandb$0.30$1.20197K197K
zenmux · minimax$0.30$1.20$0.03$0.375205K131K
ollama-cloud205K131K
qiniu-ai · minimax205K128K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02openrouterCache read$0.15
2026-09-06openrouterCache read$0.027
2026-09-02openrouter · minimaxCache read$0.027
2026-09-10openrouter · minimaxCache read$0.03
2026-09-13openrouter · minimaxCache read$0.027
2026-09-02openrouterInput$0.30
2026-09-06openrouterInput$0.27
2026-09-02openrouter · minimaxInput$0.27
2026-09-10openrouter · minimaxInput$0.30
2026-09-13openrouter · minimaxInput$0.27
2026-09-02openrouterOutput$1.10
2026-09-06openrouterOutput$1.08
2026-09-02openrouter · minimaxOutput$1.08
2026-09-10openrouter · minimaxOutput$1.20
2026-09-13openrouter · minimaxOutput$1.08

Other listings of this model

same model, different key

More from MiniMax

most-hosted first