modelbenchmark.io

MiMo V2.6 Pro UltraSpeed

mimo-v2-6-pro-ultraspeed

Compare

MiMo pro model for strong multimodal reasoning and agent execution

Specification

most-agreed values

Context
1M
Max output
131K
Released
2026-09-21
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image, audio, video
Output
text

Price

US dollars per million tokens · most-agreed

Input
$4.35
Output
$8.70
Cache read
$4.35
Cache write
free

Available from 10 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
empiriolabs$4.35$8.70$4.35—1M131K—
kilo · xiaomi$4.35$8.70$0.036—1M131K—
nano-gpt · xiaomi$4.35$8.70$0.036free1M131K—
openrouter$4.35$8.70$0.036—1M131K—
openrouter · xiaomi$4.35$8.70$0.036—1M131K—
tempr · xiaomi-mimo$4.35$8.70$0.036—1M131K—
vercel · xiaomi$4.35$8.70$0.036—1M131K—
xiaomi$4.35$8.70$0.036—1M131K—
aihubmix$4.80$9.60$0.0384—1M131K—
above$5.0769$10.1538$0.0423—1M131K—

Price history

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

DateHostField$/M
2026-09-22empiriolabsCache read$21.75
2026-09-25empiriolabsCache read$4.35
2026-09-22empiriolabsInput$21.75
2026-09-25empiriolabsInput$4.35
2026-09-22empiriolabsOutput$43.50
2026-09-25empiriolabsOutput$8.70