Nousresearch
Nous: 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...
| Specifications | |
|---|---|
| Provider | Nousresearch |
| Input pricing | $1.00/M tokens |
| Output pricing | $3.00/M tokens |
| Context length | 131K tokens |
| Input modalities | text |
| Output modalities | text |
| Tokenizer | Other |
| Knowledge cutoff | 2024-08-31 |
| Content moderated | No |
| HuggingFace | NousResearch/Hermes-4-405B |
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formattemperaturetop_ktop_p