[{"id":"router-overhead-status","title":"What was measured, recorded, calculated or not measured","columns":{"$k":["key","label","unit"],"$r":[["router","Router","text"],["kind","Kind","text"],["latency","Latency","text"],["cost","Cost","text"]]},"rows":{"$k":["router","kind","latency","cost"],"$r":[["Deterministic routing policy (Agent, in process)","in-process rules","measured 2026-10-06: 1.42 µs median","$0 (no model call)"],["Jev 1.13 (TypeSafe)","hosted decision model","measured 2026-10-06: 137 ms median, p95 196 ms (246 calls over the API from one Mac; client wall time, no server time)","$0.0337 per 1,000 (list-price calculation from input tokens; the recorded run’s own cost figure agrees)"],["Claude Sonnet 5.5 (effort low, via Claude Code)","LLM router via agent CLI","recorded: 2.60 s median (82 calls)","$4.996 per 1,000 (list-price calculation)"],["Claude Haiku 4.5 (thinking on, via Claude Code)","LLM router via agent CLI","recorded: 12.54 s median (82 calls)","$8.924 per 1,000 (list-price calculation)"],["OpenRouter Auto Router / cheaper hosted inference","hosted LLM router / gateway","Not measured: no key in the environment. The harness is ready and runs when a key is set.","Not measured: no key in the environment. The harness is ready and runs when a key is set."],["Clef / Clef-Flash (local)","local router model","Not measured: no local server running.","Not measured: no local server running."]]}},{"id":"router-overhead-jev-live","title":"Jev live run: time per call and cost","columns":[{"key":"measure","label":"Measure","unit":"text"},{"key":"value","label":"Value","unit":"text"}],"rows":{"$k":["measure","value"],"$r":[["Counted calls","246 (3 repeats of the same 82 decisions, one at a time), 0 failed"],["Median time per call","136.5 ms"],["90th percentile","171.0 ms"],["95th percentile","195.7 ms"],["Fastest and slowest call","100.9 ms and 297.3 ms"],["Cold first call (new process, fresh connection)","224.7 ms"],["Median per repeat","130.3 ms, 141.7 ms, 137.1 ms (the first repeat without the cold call)"],["Input and output tokens per decision (mean)","803 and 148 (output tokens are free at the published price)"],["Cost per 1,000 decisions (calculation)","$0.0337 = 803 input tokens × 1,000 × $0.042 per million"],["Server-side time","not available: the API sends no timing header or field"]]}}]