# Hermes 3 405B

> Nous Research's fine-tune of Llama 3.1 405B, tuned for steerability rather than refusal: it follows a system prompt further than the Instruct model it is built on, which is why roleplay, persona and agent-scaffold work keep reaching for it. Reliable function calling and structured output are part of the tune, not bolted on.

Human version: https://kymaapi.com/models/hermes-3-405b
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `hermes-3-405b` — pass this as `model` in the request body
- **Creator**: Nousresearch
- **Released**: 2024-08-16
- **Context window**: 131K tokens
- **Max output**: 8K tokens per response — a hard ceiling, not a default
- **Price**: $1.35 in / $1.35 out per 1M
- **Capabilities**: tools

## Call it

```bash
curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "hermes-3-405b", "messages": [{"role": "user", "content": "Hello"}]}'
```

## See also

- All models: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md
- Other models by Nousresearch: https://kymaapi.com/models?q=Nousresearch