← All models
N

Nous: Hermes 4 70B

nousresearch/hermes-4-70b

JSONReasoningStreaming

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...

Pricing

Input

$0.13 / 1M

Output

$0.4 / 1M

Specs

Context

131,072 tokens

Input

text

Output

text

Knowledge cutoff: 2024-08-31

Released: 2025-08

Supported parameters

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formattemperaturetop_ktop_p

Open weights · HuggingFace

818 downloads/mo
192 likes
llama3 text-generation
View on HuggingFace →