Nous: Hermes 4 405B
nousresearch
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...
- Context window
- 131,072 tokens
- Input cost
- $1.00 / 1M
- Output cost
- $3.00 / 1M
- Latency (p50)
- —