Nous Models
Nous logo

Hermes 4 405B

405B

by Nous

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 <think>...</think> traces or respond directly, offering flexibility between speed and depth. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. 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.

Chat with Hermes 4 405B
Input Price$1.00/1M tokens
Output Price$3.00/1M tokens
Intelligence17.6
Coding18.1

Specifications

Technical details and pricing.

ProviderNous
Context Window131,072 tokens
Release DateAug 27, 2025
ModalitiesText

Benchmarks

10 benchmark scores from Artificial Analysis.

GPQA53.6%
MMLU Pro72.9%
HLE4.2%
LiveCodeBench54.6%
AIME 202515.3%
SciCode34.6%
LCR20.0%
IFBench34.8%
Tau226.6%
TerminalBench Hard9.8%

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Frequently Asked Questions

What is Hermes 4 405B good for?

Use Hermes 4 405B for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Hermes 4 405B cost?

Pricing is based on usage. Current rates are $1.00/1M tokens for input and $3.00/1M tokens for output.

Can I try Hermes 4 405B for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Hermes 4 405B support images or audio?

Hermes 4 405B focuses on text-based tasks.

Benchmarks and pricing are sourced from Artificial Analysis where available. OpenRouter specs are used as a fallback.