Nous: Hermes 4 405B
Nous Hermes 4 405B is a large open-weight model with tool use and function calling, but like its 70B sibling it carries no benchmark data — at $1/$3 per 1M tokens it's priced in a competitive tier, but businesses should treat it cautiously without verified performance metrics.
Assessment date: March 14, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
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.. traces or respond directly, offering flexibility between speed and depth. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs The model is instruction-tuned with an expanded post-training corpus (~60B tokens) emphasizing reasoning traces, improving performance in math, code, STEM, and logical reasoning, while retaining broad assistant utility. It also supports structured outputs, including JSON mode, schema adherence, function calling, and tool use. Hermes 4 is trained for steerability, lower refusal rates, and alignment toward neutral, user-directed behavior.
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | Other |
| Parameters | 405B |
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $1.00 | $0.001000 |
| Output | $3.00 | $0.003000 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
External Resources
Data sourced from OpenRouter API, Artificial Analysis and Hugging Face Open LLM Leaderboard. Scores are editorially curated by our team.
Last updated: March 15, 2026 7:52 pm