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 · 201 ms · 8 models
Successful calls only · 24h
35
Average successful-call latency 16864 ms
Live sell-rate rows
3
Latest supplier-price sync 2026-08-23T01:03:40.000Z
Last successful call
2026-08-27T17:53:52.000Z
A successful proxy response with recorded billing telemetry
Last handler check
2026-08-27T20:35:16.000Z
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.