Early access: features, availability, and pricing may change as Kyara Intelligence evolves.
All models
Above baseline

Nous: Hermes 4 405B

Nous Research's 405B Llama 3.1 hybrid reasoner for math, coding, and STEM.

Model ID nousresearch/hermes-4-405b
Quick start

Drop 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!" }
    ]
  }'
See the full API reference
Overview

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.

Specifications
Context window
131K tokens Standard
Cost vs catalog median
Input
2.5x
Output
2.5x
Input 18M credits / M tokens
Output 54M credits / M tokens

Multiples are relative to the catalog median; bars are scaled to the most expensive model.

Reasoning
No
Status
Current
Moderation

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.