{"i":14,"slug":"subagent-fan-out-cost","chart":{"id":"fan-out-total-cost","title":"N × per-call or per-attempt cost, by workload (calculation)","subtitle":"Small calls use medians; worker attempts use the mean. Each workload comes from a different run.","kind":"grouped-bar","unit":"usd","yLabel":"USD at list price","whisker":"minmax","series":{"$k":["name","points"],"$r":[["Claude Code minimal reply (Haiku 4.5; Sonnet 5.5 price)",{"$k":["label","value","n"],"$r":[["10 subagents",0.1352,5],["100 subagents",1.3522,5],["500 subagents",6.761,5]]}],["Claude Code · Claude Sonnet 5.5",{"$k":["label","value","n","lo","hi"],"$r":[["10 subagents",0.036,15,0.0342,0.1021],["100 subagents",0.3601,15,0.3425,1.0211],["500 subagents",1.8003,15,1.7123,5.1053]]}],["Codex CLI · GPT-6.1 Sol (medium)",{"$k":["label","value","n","lo","hi"],"$r":[["10 subagents",0.1018,15,0.054,0.2686],["100 subagents",1.0178,15,0.5404,2.6858],["500 subagents",5.089,15,2.7018,13.429]]}],["Full worker attempt · Crewshal · Sonnet 5.5",{"$k":["label","value","n","lo","hi"],"$r":[["10 subagents",28.072,33,8.8983,48.2744],["100 subagents",280.7197,33,88.9827,482.7436],["500 subagents",1403.5986,33,444.9135,2413.718]]}]]},"note":"We ran no parallel workload. Whiskers multiply observed per-unit cost ranges by N; they are scenario spreads, not confidence intervals.\n\nSmall-call costs include non-passes: Sonnet 12/15, Sol 15/15. These are per-call costs, not costs per correct answer. Each call includes its own CLI prompt, at the size used in that run.\n\nModels, flags and prompts differ across these runs. We did not test the cause of the cost difference. Do not add these bars together.\n\nWorker costs include all 33 attempts, including failures.","sourceIds":["calc-fan-out","agent-routing-overhead","agent-caching-consistency","agent-provider-h2h","agent-swebench-c1","agent-swebench-c2","price-anthropic","price-openai"]}}