/ Models

Language models

Nous: Hermes 4 70B

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...

Maker
Nousresearch
Context window
131K
Max output
Input / 1M
$0.13
Output / 1M
$0.4
1M in + 1M out
$0.53

Everything else

Max output
Input / 1M$0.13
Output / 1M$0.4
Cache read / 1M
Cache write / 1M
1M in + 1M out$0.53
Takestext
Returnstext
Toolsno
Reasoningoptional
Open weightsyes
Released2025-08-26
Knowledge cutoff2024-08-31
Retires
Catalog idnousresearch/hermes-4-70b

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models