# Claude Fable 5.1 API

> Anthropic's model for demanding reasoning and long-horizon agentic work. By Anthropic, on Revana at $3.50 in / $17.50 out per 1M tokens.

- Model id: `claude-fable-5-1`
- Kind: text (chat completions)
- Maker: Anthropic
- Endpoint: `POST https://api.revana.si/v1/chat/completions` (OpenAI-compatible, streaming supported)
- Context window: 1M tokens
- Max output: 128K tokens
- Routes: 2 (starts on the cheapest, falls back automatically)
- Page: https://revana.si/llm/claude-fable-5-1

## Price (USD per million tokens)

| Tokens | Price |
|---|---|
| Input | $3.50 |
| Cached input | $0.0875 |
| Cache write (5 min) | $4.375 |
| Cache write (1 hour) | $7.00 |
| Output | $17.50 |

A request at reasoning effort max is billed at 3× these rates.
Reasoning tokens are billed as output. Each answer's `usage.cost_usd` is the amount taken from your balance; a request with no answer costs nothing.

## Request

```bash
curl https://api.revana.si/v1/chat/completions \
  -H "Authorization: Bearer $REVANA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-fable-5-1","messages":[{"role":"user","content":"Write a haiku about routing."}]}'
```

Or any OpenAI SDK with `base_url="https://api.revana.si/v1"`. Docs: https://revana.si/chat