modelbenchmark.io

Hermes 3 70B Instruct (Deep Infra)

hermes-3-llama-3-1-70b

Compare

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

Specification

most-agreed values

Context
131K
Max output
16K
Released
2024-08-18
Knowledge cutoff
2023-12-31
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.70
Output
$0.70
Cache read
$0.204

Available from 7 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
hyperbolic$0.12$0.30——33K33K—
nano-gpt · nousresearch$0.408$0.408$0.204—66K8K—
deepinfra$0.70$0.70——131K131K—
edenai$0.70$0.70——131K16K—
kilo · nousresearch$0.70$0.70——131K16K—
openrouter · nousresearch$0.70$0.70——131K16K—
aimlapi · nousresearch$0.7406$0.7406——131K16K—

Price history

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

DateHostField$/M
2026-10-13aimlapi · nousresearchInput$0.9628
2026-10-23aimlapi · nousresearchInput$0.7406
2026-10-13aimlapi · nousresearchOutput$0.9628
2026-10-23aimlapi · nousresearchOutput$0.7406