The mental effort in estimating what model would be better is so not worth it.
I just want to switch to Claude Code, tell it to turn a .csv into a BigQuery table then cmd+tab to something else while it runs. Thinking "oh this is probably an easy task, I can /model to Sonnet to save $0.0004" is silly.
Not everything is interactive, and what the routers do is precisely take away that mental effort on repeated tasks.
The game changes when it's not just "Opus vs Sonnet", but "Opus vs GLM". The amount saved is way more than even $0.04. And it's not only money but speed. Some providers can serve GLM crazy fast - I'll even go outside of my subscription to pay extra money for the quick results.
People actually use the models for more than writing code.
I barely used Fable because of the rate limits. It just makes more sense to use Opus.
If there were no limits it would be different.
It is not to save a fraction of a penny, it is to be able to still use the model within the limit on the week for $20.