Nous: Hermes 4 405B
Nous Research's 405B Llama 3.1 hybrid reasoner for math, coding, and STEM.
nousresearch/hermes-4-405bDrop this model into any OpenAI-compatible client by setting the base URL, your API key, and the model ID below.
curl https://api.kyara-intelligence.com/v1/chat/completions \
-H "Authorization: Bearer $KYARA_INTELLIGENCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nousresearch/hermes-4-405b",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'Hermes 4 405B is a large-scale reasoning model from Nous Research, built on Meta-Llama-3.1-405B with 60B tokens of post-training focused on verified reasoning. Its hybrid mode switches between direct responses and explicit <think>...</think> reasoning traces, with strong instruction following across math, coding, STEM, and logic. A 131K token context window leaves room for long documents and multi-step problems.
- Input
- 2.5x
- Output
- 2.5x
Multiples are relative to the catalog median; bars are scaled to the most expensive model.
- Reasoning
- No
- Status
- Current
Kyara Intelligence does not add a moderation layer. Moderating what goes in and out of your integration is up to you as the developer.
Kyara routes API calls without modifying inputs or outputs, and does not log prompt or response content. You are responsible for how your app uses the models and for complying with Kyara's terms.