Anthropic's Guide to Choosing a Claude Model and Effort Level
Source
claude.dev
Author
ClaudeDevs
Date
Why it matters
Start on Opus 5.5 at medium effort, try raising effort one level before switching models, and run subagents on Haiku or Sonnet. Re-running only failures at high effort cost about $0.17 per task versus $0.29 at high for all.
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.
