modelbenchmark.io

Hermes 4 Large

hermes-4-405b

Compare

Flagship model for demanding analysis, coding, and production agent workflows

Specification

most-agreed values

Context
128K
Max output
8K
Released
2025-08-26
Knowledge cutoff
2025-11
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.30
Output
$1.20
Cache read
$0.15
Cache write
$1.25

Available from 7 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt · nousresearch$0.30$1.20$0.15128K8K
nano-gpt · thinking$0.30$1.20$0.15128K8K
cortecs$0.996$2.989128K128K
kilo · nousresearch$1.00$3.00131K118K
nebius$1.00$3.00131K131K
nebius · nousresearch$1.00$3.00$0.10$1.25131K8K
openrouter · nousresearch$1.00$3.00131K118K