Skip to content
NINJA

Hermes 4 405B

Released by Nousresearch on 26 Aug 2025.

API id nousresearch/hermes-4-405b

Input price
$1.00 / 1M tokens
Output price
$3.00 / 1M tokens
Context window
131K tokens
Longest reply
118K tokens

About this model

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...

Description from the model’s public catalogue listing.

Capabilities

Reads
Text
Writes
Text
Reasoning mode
Yes
Tool calling
No
Open weights
Yes
Cached input
$0.20 / 1M tokens

What it would cost

At list price, without caching or batch discounts.

1,000 chat replies2K tokens in, 500 out each
$3.50
Summarise 100 long reports50K tokens in, 1K out each
$5.30
A coding agent’s working day20M tokens in, 1M out
$23.00
Price your own workload on every model

Price history

No change since we started tracking prices on 30 Sept 2026.

Alternatives at a similar price

From other labs, priced within about 40% of Hermes 4 405B, with a comparable context window.