Nous: Hermes 4 405B

Nous: Hermes 4 405B is a text-only model from Nous Research with a 128k-token context window and reasoning support. It does not support tool use, and structured output availability is unconfirmed, so workflows that depend on either of those features will need a different option. The model accepts only text input, which rules it out for multimodal tasks. At $1.00 per million input tokens and $3.00 per million output tokens, the pricing sits in a mid-range bracket. The benchmark picture is thin: a blended score of 75.0 drawn from a single benchmark (EQBench at 65.2) makes it difficult to assess general capability with confidence. Buyers who specifically need strong reasoning in long-context text tasks and can tolerate limited benchmark evidence may find it worth testing, but those requiring well-validated performance across diverse tasks should wait for broader coverage before committing.