# GPT-6 Luna

> OpenAI's most efficient GPT-6 model, for focused, high-volume tasks. 1.05M context, 128K output, text, image and file input, reasoning; above 272K prompt tokens input doubles and output rises 1.5×.

Human version: https://kymaapi.com/models/gpt-6-luna
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `gpt-6-luna`: pass this as `model` in the request body
- **Creator**: OpenAI
- **Released**: 2026-09-22
- **Context window**: 1M tokens
- **Max output**: 128K tokens per response, a hard ceiling, not a default
- **Price**: $0.135 in / $0.675 out per 1M, cached input $0.0135 per 1M
- **Capabilities**: tools, vision, reasoning, caching

## Call it

```bash
curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-6-luna", "messages": [{"role": "user", "content": "Hello"}]}'
```

## See also

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