modelbenchmark.io

Hermes-4-405B

hermes-4-405b

Compare

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Specification

most-agreed values

Context
131K
Max output
8K
Released
2025-08-26
Knowledge cutoff
2024-08-31
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.00
Output
$3.00
Cache read
$1.00

Available from 7 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt · nousresearch$0.30$1.20$0.15—128K8K—
nano-gpt · thinking$0.30$1.20$0.15—128K8K—
cortecs$0.996$2.989——128K128K—
kilo · nousresearch$1.00$3.00$0.20—131K118K—
nebius$1.00$3.00——131K131K—
nebius · nousresearch$1.00$3.00$1.00—131K8K—
openrouter · nousresearch$1.00$3.00$0.20—131K118K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02nebius · nousresearchCache read$0.10
2026-10-22nebius · nousresearchCache read$1.00