modelbenchmark.io

Hermes 3 405B Instruct (Deep Infra)

hermes-3-llama-3-1-405b

Compare

Open Llama instruction model for multilingual chat, reasoning, and coding

Specification

most-agreed values

Context
131K
Max output
16K
Released
2024-08-16
Knowledge cutoff
2023-12-31
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.00
Output
$1.00

Available from 7 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
deepinfra$1.00$1.00——131K131K—
edenai$1.00$1.00——131K16K—
kilo · nousresearch$1.00$1.00——131K16K—
nebius$1.00$3.00——128K128K—
openrouter · nousresearch$1.00$1.00——131K16K—
aimlapi · nousresearch$1.058$1.058——131K16K—
venice$1.10$3.00——128K16K—

Price history

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

DateHostField$/M
2026-10-13aimlapi · nousresearchInput$1.3754
2026-10-23aimlapi · nousresearchInput$1.058
2026-10-13aimlapi · nousresearchOutput$1.3754
2026-10-23aimlapi · nousresearchOutput$1.058