Anthropic: effort levels no longer breaking prompt cache live on API, Claude Code soon
trq212 · x · 2026-09-03
An Anthropic-affiliated engineer confirmed that effort levels no longer breaking the prompt cache is now live on the API but not yet in Claude Code, expected within a day or so.
He apologized for the gap, saying he was out of office and didn't realize the fix didn't ship with the model launch. For developers relying on prompt caching to cut costs, this means raising effort levels will no longer invalidate the cache and trigger re-billing.
Related event: Anthropic ships new capabilities on API, Claude Code to follow in days(2 posts)→
More from Models
- Heterogeneous prefill/decode isn't new: dev tried 70B prefill + 7B decode in 2023, 'entirely useless' — bingxu_ · 2026-09-03
- Ex-Cursor RL Lead Joins Meta's Reasoning Team as Muse Spark 1.3 Ships — ananyaku · 2026-09-03
- Devs warn using Gemini outside official surfaces can get your entire Google account banned — GlenBradley · 2026-09-03
- ChatGPT nails a backgammon dice probability problem at 47% odds — ivan_bezdomny · 2026-09-03
- H3 Acceleration Arena needs 1,700 more votes to crown the best turbo LoRA — Obvious_Set5239 · 2026-09-03
- muse in contributor mode is the cheapest high-end model, open or closed — philfung · 2026-09-03