Loading...
Loading...
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. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) The model is instruction-tuned with an expanded post-training corpus (~60B tokens) emphasizing reasoning traces, improving performance in math, code, STEM, and logical reasoning, while retaining broad assistant utility. 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.
Price/1M
$1.50
521st cheapest
384% above median
Top 77%
Context Window
131K
145th largest
Top 63%
Input
$1.00
per 1M tokens
Output
$3.00
per 1M tokens
Blended
$1.50
per 1M tokens
Cheaper than 23% of models. Median price is $0.31/1M tokens.
Daily
$1.50
Monthly
$45.00
Context Window
131K
tokens
Larger than 37% of models
Context Window Comparison