modelbenchmark.io

voyage-4-lite

voyage-4-lite

Compare

Lightweight general-purpose embedding model optimized for latency and cost

Specification

most-agreed values

Context
32K
Max output
0
Released
2026-01-15
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.02
Output
free

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
voyage · voyage$0.02free——32K——
vercel · voyage————32K0—