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...
The figures
- Made by
- Nous
- Model ID
- nousresearch/hermes-4-405b
- Input
- $1 per million tokens
- Output
- $3 per million tokens
- Context window
- 131K tokens
- Longest answer
- 118K tokens
- Takes in
- text
- Gives back
- text
- Reasoning
- Yes
- Tool calling
- No
- Reads images
- No
- Open weights
- Yes
- Released
- 26 Aug 2025
Read on 3 Oct 2026.