I want to pay for Opus where a review needs serious reasoning and send simple work to a cheaper model. That sounds obvious until you open a tool and leave the same model selected for everything.
Anthropic launched Opus 4.5 in November 2025 at $5 per million input tokens and $25 per million output tokens. The split that makes sense to me is Sonnet implementing and Opus reviewing. I want more capability during review, and waste during routine execution annoys me.
But reserving a model for review means preparing the review. Handing over the entire repository and asking for a general opinion creates work for me too. I have to read the response, decide what applies, and separate actual problems from comments taking up space. An enormous review can be as inconvenient as a shallow one. My rule is to give the reviewer a bounded change and its expected behavior.
Token prices belong in that decision alongside repeated work. A cheap call that keeps coming back consumes attention. An expensive call full of unrelated recommendations gains nothing from using the strongest model. I still need to measure that bill before calling any combination economical.
For the next review, I define first what it needs to discover and only then how much to pay.