n

Hermes 4 405B

Aug 2025
nHermes 4 405B
Compare in
on
—per task?
$1 / $3per 1M in / out?
42 tok/sfirst token in 2.3 s?
128Kcontext

Rankingin non-thinking mode?

Alternatives?

Run it yourself

estimate
Fits on✗ 8 GB (phone, laptop)✗ 16 GB✗ 24 GB GPU✗ 48 GB GPU✗ 80 GB GPU
LicenceLlama 3 licencecommercial use with conditions

FAQ

How much does Hermes 4 405B cost?›

$1 per 1M input tokens and $3 per 1M output tokens (cheapest host: Nebius).

Is Hermes 4 405B free to use?›

There is no free API; the cheapest paid price is $1 per 1M input tokens. The weights are open, so you can run it yourself.

How good is Hermes 4 405B, and what is it best at?›

#299 of 334 in Chat & Knowledge, #125 of 239 in Coding, #161 of 242 in Agents & Tool Use, #64 of 95 in Writing & Language.

Is Hermes 4 405B better than Qwen3.5 397B A17B?›

On EQ-Bench 3, Hermes 4 405B scores 1,361.4 vs 1,413.1 — lower.

How can I use Hermes 4 405B?›

Through the API of Nebius.

What is the context window of Hermes 4 405B?›

128K tokens, with up to 118K output tokens.

When was Hermes 4 405B released? Is there a newer version?›

Released 2025-08-27. It is the current version in its line.

Is Hermes 4 405B open source?›

Yes, the weights are open (llama3 licence).

Can I run Hermes 4 405B locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

Can Hermes 4 405B read images?›

No, it accepts text only.

What is Hermes 4 405B?›

Hermes 4 405B is an open-weights language model from nousresearch, released Aug 2025.

What are the best alternatives to Hermes 4 405B?›

Hivemind 32B Preview (cheaper), Claude Fable 5 (better).