modelbenchmark.io

MiMo V2.6 Flash Abliterated

mimo-v2-6-flash-abliterated

Compare

A MiMo V2.6 Flash finetune with refusal-direction ablation, image input, a 1M-token context window, separate reasoning output, and tool calling.

Specification

most-agreed values

Context
1M
Max output
66K
Released
2026-09-25
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.50
Output
$1.50
Cache read
$0.275

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt · xiaomi$0.50$1.50$0.275—1M66K—