modelbenchmark.io

Hy3

hy3-paid

Compare

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Specification

most-agreed values

Context
256K
Max output
128K
Released
2026-07-06
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.14
Output
$0.58
Cache read
$0.035

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
commandcode · tencent$0.14$0.58$0.035—256K128K—