Home › AI Models › Nousresearch › Nous: Hermes 4 405B
Nousresearch

Nous: Hermes 4 405B

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](https://ask-coreai.com) 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.

Context Window
131K tokens
Parameters
405B
Input Price
$1.00/1M
Output Price
$3.00/1M
Price Tier
standard
Provider
Nousresearch

How to Use Nous: Hermes 4 405B

With CoreAI, you can start chatting with Nous: Hermes 4 405B instantly — no separate subscription needed. CoreAI bundles access to Nous: Hermes 4 405B along with 300+ other AI models from Nousresearch and other providers like OpenAI, Anthropic, Google, Meta, and more.

  1. Download the CoreAI app for iOS, Android, or use the Web App
  2. Select Nous: Hermes 4 405B from the model selector
  3. Start chatting, comparing, or creating with AI

More Nousresearch Models

Nousresearch

Nous: Hermes 4 70B

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 releas
131K budget
Nousresearch

Nous: Hermes 3 70B Instruct

Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced
131K budget
Nousresearch

Nous: Hermes 3 405B Instruct (free)

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reason
131K budget
Nousresearch

Nous: Hermes 3 405B Instruct

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reason
131K standard
Nousresearch

NousResearch: Hermes 2 Pro - Llama-3 8B

Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well a
8K budget

Try Nous: Hermes 4 405B Now

Chat with Nous: Hermes 4 405B and 300+ other AI models — all in one app.

Download App → Try on Web App