Back to all models
nousresearch
nousresearchNous: 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...
nousresearch/hermes-4-70b
Context Size
131.072K
Input Price
19,500 pts/M
Output Price
60,000 pts/M
Architecture
Text
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formattemperaturetop_ktop_p
Details
TokenizerLlama3
Provider Context131.072K tokens
ModeratedNo
CreatedAug 26, 2025