How to decide Opus vs Sonnet for every task

A decision rubric, not a vibe check

Run the free audit →

What's going on

Opus is 5x the price of Sonnet. 8% of tasks need Opus. The other 92% are Sonnet-or-Haiku jobs paid at Opus prices. Here's how to route.

What to do about it

Three patterns dominate the waste on most Claude workloads: (1) context re-sending; (2) retry loops on validation failures; (3) agent-chain re-reads. AIUsage's audit identifies which is eating your bill and projects what you'd save — no signup required for the number.

The fastest path to your real number: paste your last 30 days of Anthropic usage at aiusage.ai. Under two minutes. If your expected delta is under 40%, the audit says so and you walk.
Audit my Claude usage →