Claude Fable 5.1 changelog

Full Claude Platform available on Google Cloud (Anthropic managed)

Claude Models on Google Cloud (Anthropic managed) is generally available with US and Global endpoints. It gives Google Cloud customers the full Claude Platform feature set with Google Cloud IAM, billing and commitment drawdown. Fable 5.1, Opus 5.5, Sonnet 5.5 and Haiku 5.5 are available, and fast mode for Opus 5.5 costs $8 / $40 per million input and output tokens there.

Who is affected:

Teams that buy Claude through Google Cloud and want features that the Google-managed offering lacks.

What to do:

No action needed. Google Cloud customers who need same-day Claude API features can switch to the Anthropic-managed offering.

Claude Code makes Fable 5.1 the default Fable model

Claude Code 2.1.257 added Claude Fable 5.1 as the default Fable model with a 1M context window at $10 / $50 per million tokens.

Who is affected:

Claude Code users on the fable alias.

What to do:

Update Claude Code. Fable 5.1 needs version 2.1.255 or later.

Claude Fable 5.1 released as the successor to Fable 5

Claude Fable 5.1 (and Claude Mythos 5.1 for Project Glasswing participants) launched at the same $10 / $50 per million tokens as Fable 5, with cache reads cut to $0.25 per million tokens.

Who is affected:

Teams using Claude Fable 5 on the API or in the Claude apps.

What to do:

Move from claude-fable-5 to claude-fable-5-1 after checking the tool_choice and thinking-block changes.

Fable 5.1 drops forced tool use and binds thinking blocks to history

On Fable 5.1 and Mythos 5.1, tool_choice any and tool return a 400 error. For accounts created on or after August 31, 2026, replaying a thinking block after the system prompt, tools or earlier messages changed also returns a 400 error.

Who is affected:

Code moving from Fable 5 to Fable 5.1, especially agents that rewrite history or force tool calls.

Action needed:

Use tool_choice auto with strict tool use, and stop editing context before thinking blocks.

New API accounts can no longer edit context around thinking blocks

To counter distillation, the API now checks that a thinking block is sent back with the same system prompt, tools and messages. On Fable 5.1, Opus 5.5, Sonnet 5.5 and Haiku 5.5, accounts created on or after August 31, 2026 get an error unless they opt into dropping the block.

Who is affected:

Agents that compact or rewrite earlier turns, especially on new API accounts.

Action needed:

Use server-side compaction or mid-conversation tool changes, or opt into non-strict mode.

Claude Fable 5.1 available in GitHub Copilot, with data retention by default

Claude Fable 5.1 is available on Copilot Pro+, Max, Business and Enterprise. Unlike other Claude models in Copilot it requires data retention so Anthropic can run safety classifiers. Eligible enterprises can use zero data retention through the end of 2026.

Who is affected:

Copilot organizations with zero data retention requirements.

What to do:

Copilot admins: review the data retention terms before enabling the Fable 5.1 policy.