modelbenchmark.io

Mellum2 12B A2.5B

mellum2-12b-a2-5b-instruct

Compare

Mellum2-12B-A2.5B-Instruct is a fast MoE model with 131K context built for coding, tool use, and low-latency AI workflows.

Specification

most-agreed values

Context
131K
Max output
131K
Released
2026-06-01
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.05
Output
$0.10
Cache read
$0.05

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
wandb · jetbrains$0.05$0.10$0.05131K131K
wandb · wandb$0.05$0.10131K