What a Claude Code task really costs on Opus 5.5: cache hit rate is everything

xiaohu · x · 2026-09-23

A breakdown based on Addy Osmani's post at Anthropic. Opus 5.5 cut API prices across the board: fresh input $4/M (-20%), output $20/M (-20%), cache reads $0.20/M (-60%, just 5% of fresh input).

For a representative 40-turn task averaging 70K tokens per turn (2.8M cumulative input), paying all fresh input would cost $11.20; at a 90% cache hit rate input drops to $1.62. The key insight: Claude Code's cost blowup comes from re-sending history every turn, so maximizing prompt cache hits is the biggest lever, followed by fewer turns and less output (thinking is billed as output). Also covers effort tuning, model choice and /usage, with two reusable templates.

Related event: Anthropic's Opus 5.5 guide: hand over whole tasks, intervene less, effort defaults to medium(7 posts)→

Original post →

More from coding & agent

coding & agent channel →