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... Hybrid reasoning mode auto-decides when to think deeply Strong instruction following and tool use Open-weight on Llama 3.1 405B base Uncensored no refusal for controversial topics Based on older Llama 3.1 architecture Very large model slow and expensive to run Less competitive on raw benchmarks vs latest models Complex multi-step reasoning Creative and uncensored writing Research and experimentation Tool-use and agentic workflows
Specifications
| Lab | Nousresearch |
|---|---|
| Context window | 131,072 |
| Input price | $1.00/1M |
| Output price | $3.00/1M |
| Release | 2025-08-01 00:00:00 |
Strengths
- Hybrid reasoning mode auto-decides when to think deeply
- Strong instruction following and tool use
- Open-weight on Llama 3.1 405B base
- Uncensored no refusal for controversial topics
Weaknesses
- Based on older Llama 3.1 architecture
- Very large model slow and expensive to run
- Less competitive on raw benchmarks vs latest models
Best for
- Complex multi-step reasoning
- Creative and uncensored writing
- Research and experimentation
- Tool-use and agentic workflows
In Depth: Nous: Hermes 4 405B
Summary
Nous: Hermes 4 405B is an AI model from Nousresearch.
Released 2025-08-01 00:00:00. It currently appears in the Overall category on LMRank. It supports Text input and produces Text output, with a context window of 131.1K tokens. Input pricing is $1.00 per 1M tokens and output is $3.00 per 1M tokens on OpenRouter.