Nous: Hermes 4 405B

Nous: Hermes 4 405B

nousresearch · Released Aug 26, 2025 Legacy
Intelligence #387 / 551
23.8 Our Score
Speed
Not reported
Input #417 / 552
$1.00 per 1M tokens
Output #410 / 552
$3.00 per 1M tokens
Context #206 / 552
131,072 tokens

Analysis Summary

Nous: Hermes 4 405B sits in the Legacy tier on our leaderboard, ranked #387 of 551 published models on overall intelligence. At $1.00 input and $3.00 output per 1M tokens, it is among the most expensive on the market. It offers a standard large context window.

Editorial notes

Nous Hermes 4 405B is a large model from NousResearch at $1/$3 with a 131K context window, but lacks benchmark data entirely; provider reputation is modest and no capability signals are available to justify a higher score.

Assessed May 5, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence0Technical0Value6.8Content4
Intelligence 0/10
Technical 0/10
Content 4/10
Value 6.8/10

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..

405B Parameters

How does Nous: Hermes 4 405B stack up?

Compare side-by-side with other legacy models.

Compare Models

Model Information

OpenRouter ID nousresearch/hermes-4-405b
Providernousresearch
Release Date August 26, 2025
Context Length131,072 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $1.00 $0.001000
Output $3.00 $0.003000

Live Performance

Live endpoint metrics — refreshed every 30 minutes.

100%
Avg Uptime
287ms
Best Latency (TTFT)
27.5 tok/s
Best Throughput
1/1
Active Endpoints
Available via: Nebius