> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apiyi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Fable 5.2 Is Live: 20% Cheaper, 30% Faster

> Claude Fable 5.2 is live on APIYI at $8 input / $40 output per 1M tokens, 20% below 5.1, with $0.20 cache reads. It keeps the 1M context window and 128K output, generates up to 30% faster, and lifts FrontierCode 2.0 to 49.1%. Both model IDs are available in four groups.

**2026/11/10 15:52 (UTC+8)** · New Model · Anthropic

🚀 **Claude Fable 5.2 is live on APIYI at \$8 input / \$40 output per 1M tokens, 20% below 5.1**

Anthropic released Fable 5.2 on November 9 with a 1M-token context window, 128K max output, and generation up to 30% faster than 5.1; FrontierCode 2.0 rises from 32.4% to 49.1%. `claude-fable-5-2` and `claude-fable-5-2-thinking` are available in the `ClaudeCode`, `Claude_Enterprise`, `Default`, and `SVIP` groups, with cache reads at \$0.20 per 1M tokens and all four billing items matching the official list. `Claude_Enterprise` is the more stable Claude official-passthrough group for enterprise support and emergency needs, at a 1.2x multiplier.

Two breaking changes return errors when migrating from 5.1: the prefix check now applies to every account, and thinking blocks are tied to the model that produced them. The `Claude_Reverse` group is not available yet.

***

← [Back to Live Updates](https://docs.apiyi.com/en/live.md) · 📚 [Monthly archive](https://docs.apiyi.com/en/live/archive.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.