RT @claudeai: One more thing: we’re halving the price of cache reads on Claude Sonnet 5.5, to $0.10 per million tokens. That makes Sonnet 5.5 around 20% cheaper to run on most long-running work.
Why CEREBRO kept it
Prompt cache read price halved, direct token-optimization signal
The text below is an automated extraction of the article at https://x.com/bcherny/status/2107976985104580747, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (x.com).
RT @claudeai: One more thing: we’re halving the price of cache reads on Claude Sonnet 5.5, to $0.10 per million tokens. That makes Sonnet 5.5 around 20% cheaper to run on most long-running work.
Backlinks
Appeared in 1 briefing