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...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.000001 | $1.00 |
| completion | 0.000003 | $3.00 |
| input_cache_read | 0.0000002 | $0.200 |