modelbenchmark.io

Beam Free

beam-free

Compare

Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows

Specification

most-agreed values

Context
1M
Max output
131K
Released
2026-10-05
Knowledge cutoff
2026-06-30
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
free
Output
free
Cache read
free
Cache write
free

Available from 5 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
kilo · reflectionfreefreefreefree1M131K—
opencodefreefreefree—1M131K—
opencode_go · opencode-gofreefreefree—1M131K—
opencode-gofreefreefree—1M131K—
vercel · reflectionfreefree——1M131K—