Then there is the choice of who does each job.
Model routing
Sending each job to a model that fits it, instead of one model for everything: a cheap one for searching and summaries, an expensive one for planning and hard bugs. The router can be a rule, a setting or a person.
The prices differ by up to a hundred times, so on tokens alone routing nearly always wins. The danger is a cheap model that fails without saying so. A failure you see costs one retry. A failure that passes for success costs whatever it breaks later. Route freely where a check can catch it.
“Set model: haiku on the search subagent and leave planning on opus. Run our 10 sample tasks both ways, score them with bun test and the holdout scenarios, and show me cost per passing task for each. If the routed version misses anything the tests catch, keep that step on the bigger model.”