Product update · 2026-08-27

Observed service status published

A public evidence page now reports no-token endpoint checks and successful-call telemetry.

What changed

The monitor calls GET /v1/models and spends no model tokens.
No synthetic uptime percentage is claimed.
Verification limitations remain visible beside the measurements.

Use it

Open the live feature.

All product updates

Successful API requests are billed at the displayed token rates, metered to a fraction of a cent. Charges accumulate and are deducted from your prepaid balance in whole US cents, so a small request is not rounded up to a minimum charge.