Nous: Hermes 3 405B Instruct is a generalist language model representing a significant advancement over Hermes 2. It boasts advanced agentic capabilities, much better roleplaying, enhanced reasoning, improved multi-turn conversation, and long context coherence. This model is a frontier-level, full-parameter finetune of the Llama-3.1 405B foundation model, specifically aligned to empower users with powerful steering and control. The Hermes 3 series expands on its predecessor's strengths, including more powerful and reliable function calling, structured output capabilities, generalist assistant functions, and refined code generation skills. With a context window of 131K tokens and a max output of 4K tokens, it supports streaming and search capabilities. Pricing is set at $1.00/1.00 per 1M tokens (input/output), making it accessible under the STARTER access tier. Hermes 3 is competitive, if not superior, to Llama-3.1 Instruct models in general capabilities, offering distinct strengths for various applications.
✅ Best For
🚀 Capabilities
❌ Limitations
Specifications
| Provider | nousresearch |
| Context Window | 131,072 tokens |
| Max Output | 16,384 tokens |
| Minimum Plan | Balance |
Pricing
| Input Price | $1.0000 / 1M tokens |
| Output Price | $1.0000 / 1M tokens |
💡 With PRO subscription, cost is reduced by 20%