Claude Fable 5.2 is now available on Entire. Starting today, you can select it to create custom review agents in Trails, our alternative for the pull request that puts confidence evals at the center of review.
Trails let you define what a change needs to satisfy and configure custom agents to review it against those criteria. Use them to check for slop, security issues, drift, or any configuration you desire, and your custom agents score your code changes accordingly on every push.
With Claude Fable 5.2, Anthropic reports strong improvements in coding and reasoning. At High effort, Claude Fable 5.2 scores about level with Opus 5.5 at Max effort, for roughly half the cost per task. The model’s standard API pricing is $8 per million input tokens and $40 per million output tokens, 20% lower than Fable 5.1’s rates.
More information on pricing for Entire can be found in our docs.
Try It on Your Next Trail #
To get started, select Claude Fable 5.2 when creating a custom review agent for your projects in our web UI on entire.com, or configure directly from your coding agent. As always, let us know what you think by joining our Discord today.