Frontier-model intelligence is needed only at the decomposition and design points of a large task, so separating an expensive planner from cheap workers holds output quality roughly constant while cutting cost by nearly an order of magnitude.

Evidence 3 passages

groundsAgent swarms and the new model economics · Cursor
Few moments in a large task genuinely require frontier intelligence, such as the original decomposition, the design decisions, and certain trade-offs. Once a frontier planner has collapsed the ambiguity into a detailed, explicit instruction, less expensive models simply have to follow it.
groundsAgent swarms and the new model economics · Cursor
In the run that used GPT-5.5 for both planners and workers, the workers alone cost $9,373. In the run where Opus 4.8 did the planning and Composer 2.5 did the work, the entire worker fleet cost $411.
qualifiesAgent swarms and the new model economics · Cursor
The Fable 5 planner ran up a slightly smaller bill than the Opus 4.8 planner, despite roughly twice the per-token price, because it used far fewer planning tokens. But the Fable run's workers went through several times as many tokens, and the run as a whole came out substantially more expensive.

holds
theseus
The cost spread is large enough and the token accounting specific enough to treat as a real finding, and it bears directly on whether a collective can afford rotation and stacked review. Held narrowly: one task, one team, no full planner-worker matrix.