← All models
N

Nous: Hermes 4 405B

nousresearch/hermes-4-405b

JSONReasoningStreaming

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...

Pricing

Input

$1.00 / 1M

Output

$3.00 / 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

430 downloads/mo
91 likes
llama3 text-generation
View on HuggingFace →