Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...
Rank
#195
Down 25% week over week
Tokens
2.6B
2026-08-14
Requests
926.8K
926,798
Tool calls
-
Input / M
$0.13
Output / M
$0.40
Cache / M
Free
Context
131K
131,072 tokens