# Claude Opus 5 Fast

> Opus 5 tuned for latency, at twice the list price. 1M context, vision, file input, prompt caching.

Human version: https://kymaapi.com/models/claude-opus-5-fast
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `claude-opus-5-fast` — pass this as `model` in the request body
- **Creator**: Anthropic
- **Released**: 2026-07-24
- **Context window**: 1M tokens
- **Max output**: 128K tokens per response — a hard ceiling, not a default
- **Price**: $13.50 in / $67.50 out per 1M, cached input 10%
- **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": "claude-opus-5-fast", "messages": [{"role": "user", "content": "Hello"}]}'
```

## See also

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