Back to all models
nousresearch
nousresearchNous: Hermes 4 405B
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...
nousresearch/hermes-4-405b
Context Size
131.072K
Input Price
150,000 pts/M9,225 Ks/M
Output Price
450,000 pts/M27,675 Ks/M
Architecture
Text
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formattemperaturetop_ktop_p
Details
TokenizerOther
Max Completion117,964 tokens
Provider Context131.072K tokens
ModeratedNo
CreatedAug 26, 2025