Claude Fable 5 now available on AI Gateway
By Steven Van ·
Anthropic's newest Claude model reaches Vercel's AI Gateway, with stronger multi-step performance but no Zero Data Retention support.
Anthropic's Claude Fable 5 is now available through Vercel's AI Gateway. It's a Mythos-class model that Anthropic positions as a step up over prior Claude models on long-running, ambiguous, multi-step tasks, able to execute end-to-end on work that previously needed frequent human check-ins.
- The model sustains productive output across multi-day runs and dispatches parallel sub-agents reliably; lower effort settings often match what prior Claude models produced at their highest effort.
- Code review, bug-finding, and repository investigation are stronger, with noticeably higher first-shot correctness on complex problems.
- It ships with blocking classifiers that refuse offensive cybersecurity, biology, and summarized-thinking extraction requests, reflecting misuse risk in those areas.
- It does not support Zero Data Retention: prompts and completions are retained for 30 days, though they are not used to train Claude.
To use it, developers set the model to anthropic/claude-fable-5 in the AI SDK.
Vercel
The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.
View Vercel →