Per-route DLR-rate anomaly classification (drop/normal/insufficient_data)
Compares the last COMPLETE day’s delivery rate on every outbound SMS route (carrier provider × destination country) against a learned 14-day baseline (z-score with a floored stddev, plus relative-ratio and absolute-points guards) and flags it drop, normal or insufficient_data. Use it to catch a carrier silently degrading one route — a blocked sender, a filtering change, an upstream wholesale outage — before customers open a ticket; the daily webhook-worker scheduler pages on the same classification. No query parameters. Restricted to owner/admin/developer/viewer; read-only, rate-limited, 60s cached.
Authorizations
Dashboard JWT token from Clerk
Headers
Sandbox opt-in for Clerk-session-authenticated requests. Set to true to route the call through the test-mode pipeline: no real provider delivery, no credits deducted, response meta.test_mode: true. Ignored for live API keys (dv_live_sk_*) — server-to-server clients must use a test-prefixed key (dv_test_sk_*) to exercise sandbox. Test-prefixed keys unconditionally enable sandbox regardless of this header.
true, false Response
Standard { data, meta } envelope. Per-route decisions (drop first, then most-negative z-score) with the summary rollup.