Description
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.
API Usage Examples
OpenAI Compatible Endpoint
Use this endpoint with any OpenAI-compatible library. Model: Nous: Hermes 4 405B (nousresearch/hermes-4-405b)
curl https://api.ridvay.com/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d '{
"model": "nousresearch/hermes-4-405b",
"messages": [
{
"role": "user",
"content": "Explain the capabilities of the Nous: Hermes 4 405B model"
}
],
"temperature": 0.7,
"max_tokens": 1024
}'Supported Modalities
- Text
API Pricing
- Input: 0.2$ / 1M tokens
- Output: 0.8$ / 1M tokens
Token Limits
- Max Output: 131,072 tokens
- Max Context: 131,072 tokens
Subscription Tiers
- free
- pro
- ultimate