modelbenchmark.io

Hermes 3 70B

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

Compare

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

Specification

most-agreed values

Context
66K
Max output
8K
Released
2026-01-07
Knowledge cutoff
2023-12-31
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.408
Output
$0.408
Cache read
$0.204

Available from 5 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
hyperbolic$0.12$0.3033K33K
nano-gpt · nousresearch$0.408$0.408$0.20466K8K
deepinfra$0.70$0.70131K131K
kilo · nousresearch$0.70$0.70131K16K
openrouter · nousresearch$0.70$0.70131K16K

Other listings of this model

same model, different key