What's new in Claude Fable 5.1: Points: 1 # Comments: 0

What shipped in What's new in Claude Fable 5.1

* Intro Paragraph 2 (What it covers & Who it is for): This article covers the technical architecture, operational improvements, and installation procedures for Claude Fable 5.1. It is written specifically for software architects, tool builders, and integration engineers who require reliable, low-latency language models for automated

Copy pageClaude Fable 5.1 extends Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep research, and document, spreadsheet, and slide work. Use Claude Fable 5.1 for demanding reasoning and long-horizon agentic work, or when your evals on Claude Opus 5 at higher effort still fall short.

What improved in What's new in Claude Fable 5.1

Claude Mythos 5.1 offers the same capabilities to Project Glasswing participants only. If you already call Claude Fable 5, three changes are breaking: forced tool use returns an error, earlier models can't read its thinking blocks, and editing earlier turns invalidates thinking blocks.

What you gain from What's new in Claude Fable 5.1

Five are additive: per-message effort (beta), turn-scoped system messages (beta), readable progress updates between tool calls (display: "updates", beta), a lower cache read price, and content provenance. See the full write-up from HN Claude/Codex/Fable via the source link for quotes and complete context.

How to get What's new in Claude Fable 5.1

Pricing: the same as Claude Fable 5, except for a lower cache read price. Tokenizer: the same as Claude Fable 5 (introduced with Claude Opus 4.7).

What to watch after What's new in Claude Fable 5.1

Compared with models older than Claude Opus 4.7, the same text produces roughly 30% more tokens. Breaking changes Forced tool use is not supported Claude Fable 5.1 and Claude Mythos 5.1 don't support forced tool use.