modelbenchmark.io

Tencent Hy4 Preview

hy4

Compare

A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.

Specification

most-agreed values

Context
1M
Max output
64K
Released
2026-08-28
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.834
Output
$2.501
Cache read
$0.042
Cache write
$0.96

Available from 11 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
vancine$0.67$2.00$0.0341M64K
kilo · tencent$0.834$2.501$0.0421M64K
llmgateway$0.834$2.501$0.0421M64K
llmgateway-providers · tencent$0.834$2.501$0.0421M66K
nano-gpt · tencent$0.834$2.501$0.0421M64K
opencode-go$0.834$2.501$0.0421M64K
openrouter · tencent$0.834$2.501$0.0421M64K
tencent-token-plan$0.834$2.501$0.0421M64K
tencent-tokenhub$0.834$2.501$0.0421M64K
vercel · tencent$0.834$2.501$0.0421M64K
crossmodel · tencent$0.96$2.88$0.048$0.961M66K