Nous: Hermes 4 70B reasoning
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...
Capabilities
Context Window 131k tokens
Max Output 0 tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $0.13
Output $0.40
Cache Read -
Cache Write -
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formattemperaturetop_ktop_p