nousresearchListed Aug 26, 2025

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...

Context window131.1K
Max output118K
Parameters405B
Provider endpoints2
Benchmark results0
Measured performance

Benchmark results

All leaderboards ↗
—

No published results in this index yet

Scores appear here when an evaluation matches this exact model.

Access & cost

Prices across providers

2 quotes

OpenRouter

Catalog quote
Input
$1.00
Output
$3.00
USD / 1M tokens
131.1K context118K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDnousresearch/hermes-4-405b

Nebius

via OpenRouter

nebius/fp8 · quantization=fp8

Input
$1.00
Output
$3.00
USD / 1M tokens
131.1K context118K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDnousresearch/hermes-4-405b::nebius/fp8

Model specifications

Developer
nousresearch
Modality
Language
Context
131,072 tokens
Maximum output
117,964 tokens
Weights
Open weights
Provider listed
Aug 26, 2025
First discovered
Oct 16, 2026

Exact identities

  • openrouternousresearch/hermes-4-405b

Sources

Updated Oct 17, 2026

More from nousresearch

View all ↗
nousresearchListed Jul 29

Nous: Hermes 3 70B Instruct

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence,…

131.1K context70BStructured outputOpen weightsNo reported score
No reported score
$0.70in$0.70out/ 1M tokens · USDdeepinfra · via Hugging Face · 5 endpoints