# Gemini 4 Argon

> Google's flagship reasoning model, built for complex software engineering, math and science problems, and autonomous multi-step agents. 1M context, 64K output, text, image, audio, video and file input, reasoning, tool calling, structured outputs.

Human version: https://kymaapi.com/models/gemini-4-argon
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `gemini-4-argon`: pass this as `model` in the request body
- **Creator**: Google
- **Released**: 2026-10-13
- **Context window**: 1M tokens
- **Max output**: 66K tokens per response, a hard ceiling, not a default
- **Price**: $2.70 in / $13.50 out per 1M, cached input $0.135 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": "gemini-4-argon", "messages": [{"role": "user", "content": "Hello"}]}'
```

## See also

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