Effective Oct 7 2026, Claude Sonnet 5.5 prompt cache reads cost $0.10 per million tokens, down from $0.20.
NoteBy OossaPublished by Oossa: 1 min read
Event date:
Anthropic announced a price cut for using prompt caching with its Claude Sonnet 5.5 model. The cost to read cached prompts is now $0.10 per million tokens, half the previous $0.20 rate. Writes to the cache and all other pricing remain the same. The change is reflected in the API release notes published on Oct 7 2026.
Developers can reduce API costs when reusing prompts, making large‑scale Claude Sonnet 5.5 deployments cheaper.
Business
A year‑long Senate probe found developers often inflate construction job numbers and hide permanent staffing data.
Business
Clef‑omni can handle text, images, audio and video in one API call; Clef‑flash now costs $0.038 per million tokens, and the original Clef model is faster.
Business
Amazon says it will no longer use nondisclosure agreements when striking data‑center deals, following Microsoft’s similar policy earlier this year.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
