Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
Rank
#240
Up 161% week over week
Tokens
1.0B
2026-08-14
Requests
466.5K
466,495
Tool calls
-
Input / M
$1.00
Output / M
$3.00
Cache / M
Free
Context
131K
131,072 tokens