Claude Fable 5.1 cuts the cost of cached context
Headline token pricing remains premium while published cache-read pricing falls to $0.25 per million tokens.
By Aaron Felix · Updated 7 October 2026
What this changes for UK buyers
Persistent agents and large-codebase workflows may have different economics from one-shot prompts.
What buyers should do
Measure cache-hit rate and total cost per accepted task instead of comparing headline token prices.
Primary announcement
Anthropic launch announcement ↗This is a dated source-linked buyer briefing. A vendor announcement does not prove UK account eligibility, an independent performance result or regulatory compliance. Open the primary source and confirm the exact plan before changing a production workflow.
Related profiles
Evidence standard · Commercial disclosure · Send a correction