# Claude Fable 5.1

## Best for

Coding agents, front-end work, and research-heavy tasks

## When not to use

Zero data retention. Image, audio, or video input on this route — text only. Not Opus 5 when the job is the heaviest reasoning or parallel-subagent coordination. Call it as `claude-fable-5.1`.

## Overview

Non-ZDR: upstream providers may retain prompts and outputs.

Claude Fable 5.1 improves on Fable 5 most in coding agents, long-running tasks, front-end generation, and analysis work. Its plans and summaries also tend to be shorter. Try it as a replacement for Fable 5, or use it alongside Opus 5 for tasks that need more reasoning.

| | |
| --- | --- |
| API identifier | `claude-fable-5.1` |
| Developer | Anthropic |
| Context window | 262,144 tokens |
| Supports | text, reasoning, tool-use |
| Status | Serving |

## Rates

USD per 1M tokens, on-demand tier.

| Input | Cached input | Output |
| --- | --- | --- |
| $10.00 | $0.25 | $50.00 |

## Call it

Put `claude-fable-5.1` in the `model` field. The same request works against the Anthropic Messages API — see [API Compatibility](https://inference.boundless.network/docs/api-compatibility).

```bash
curl https://api.inference.boundless.network/v1/chat/completions \
  -H "Authorization: Bearer $BOUNDLESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-fable-5.1",
    "messages": [{
      "content": "Say hello",
      "role": "user"
    }]
  }'
```

Every model we serve is listed at [Models](https://inference.boundless.network/models); the rate card in full is on [Pricing](https://inference.boundless.network/docs/pricing).