Nous: Hermes 4 70B
Nous Hermes 4 70B is a fine-tuned open-weight model with tool use support, but the absence of benchmark data means we cannot verify its real-world performance — it may appeal to developers building on open-source foundations, but cannot be recommended for business-critical applications without further evaluation.
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 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either respond directly or generate explicit.. reasoning traces before answering. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs This 70B variant is trained with the expanded post-training corpus (~60B tokens) emphasizing verified reasoning data, leading to improvements in mathematics, coding, STEM, logic, and structured outputs while maintaining general assistant performance. It supports JSON mode, schema adherence, function calling, and tool use, and is designed for greater steerability with reduced refusal rates.
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | Llama3 |
| Parameters | 70B |
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.13 | $0.000130 |
| Output | $0.40 | $0.000400 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
