Evidence, not an SLA
Observed service status
Read-only operational evidence. This page does not claim synthetic uptime, contractual availability, or model identity.
Models handler
Ready
Handler 200 · 205 ms · 8 models
Successful calls only · 24h
0
Average successful-call latency 0 ms
Live sell-rate rows
11
Latest supplier-price sync 2026-10-15T03:10:03.000Z
Last successful call
No successful customer call recorded
A successful proxy response with recorded billing telemetry
Last handler check
2026-10-15T07:20:12.000Z
Measurement limits
- The scheduled check exercises the Worker's
GET /v1/modelshandler internally. It spends no model tokens, does not verify external DNS or TLS, and does not prove that every upstream model can complete a request. - Successful-call counts come from billing telemetry after completed customer calls. Failed calls are not currently included in this aggregate.
- Latency is the observed upstream round trip for successful calls, not a guaranteed maximum.
- No uptime percentage is shown until a sufficiently continuous first-party series exists.
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.