Fable 5 API
API facts are only half the workflow
Claude docs list Fable 5 as an API model. The model string, context window, output ceiling, and price matter, but production work also needs briefs, logs, reviews, and reusable task history.
Quick summary
- Model string: claude-fable-5.
- Claude docs list a 1M context window and 128K max output.
- Published API pricing should be checked against the official docs before running high-volume jobs.
Use the API for structured jobs
Fable 5 should be especially interesting for multi-step jobs: migration planning, code review, source synthesis, product specs, and artifact creation. Those jobs benefit from explicit input bundles and review gates.
Do not hide model cost
If a task may consume a large context window or long output, the workflow should show what is being sent, why it matters, and which result will be reviewed before more work runs.
Clef route
Clef can sit above first-party model surfaces and local CLIs. The user brings provider access; Clef keeps task context, source cards, run evidence, and handoff.
Turn the search into a workflow
Clef is testing a product layer for people who want frontier models to produce reviewable work, not just impressive chat answers.
Build a Fable 5 workflowFAQ
Does Clef resell Fable 5 API access?
No. API access remains with Anthropic. Clef is the workflow and review layer around the work.
Should I build directly on the API or use a workbench?
Use the API directly for simple calls. Use a workbench when the task has sources, files, reviews, or handoff.
Sources and status
This page is independent and not affiliated with Anthropic. Fable 5 facts should be checked against official sources before production decisions.