Hermes 3 405B is Nous Research's full-parameter fine-tune of Meta's Llama 3.1 405B, focused on aligning the model to the user with strong steering and control. It improves agentic behavior, roleplay, reasoning, multi-turn conversation and long-context coherence, and supports function calling and JSON structured outputs.
Private|128K context|$1.10/M input|$3.00/M output