AI model · Nous
Hermes 4 405B
Model ID: nousresearch/hermes-4-405b
- Input
- $1 per 1M tokens
- Output
- $3 per 1M tokens
- Context
- 131K tokens at once
- Max output
- 118K tokens per reply
- Released
- 26 Aug 2025 Nous
What it can do
- YesReasoning
- NoTool calling
- NoImage input
- YesOpen weights
- NoFree to use
Takes text; gives text.
How its listing describes it
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...
Sources
- Nous: Hermes 4 405B on OpenRouter — read 2 Oct 2026