modelbenchmark.io

LFM2-24B-A2B

lfm2-24b-a2b

Compare

Efficient open Liquid MoE instruct model for on-device chat and tool calling

Specification

most-agreed values

Context
33K
Max output
33K
Released
2026-02-24
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.03
Output
$0.12

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
togetherai · liquidai$0.03$0.12——33K33K—