Lately, I've been investigating 'serverless' databases (PlanetScale, Turso) that charge based on the number of rows read/scanned. As a result, instead of just relying on the perceived performance of a query, I've started monitoring the number of rows scanned, which has emphasized the importance of indexes to me. Granted, the cost per rows read is minuscule (PlanetScale charges $1 per billion!), but it's still something I keep in mind.