Tom & Jerry · AI Infrastructure

AI Status

AI API operational
Synthetic model checks are passing.

Availability

Synthetic probe · gpt-5.6-sol
Last 60 Minutes 1h uptime 100.00%
60 minutes agoNow

Capacity

5h
resets 22:10 UTC+08
21.0%Available
Weekly
resets Jul 19 17:10 UTC+08
88.0%Available
24h uptime 96.89%
1h p95 latency 2.63s
Diagnostics Gateway load, upstream dependencies, recent checks and status events

Probe Details

Successful checks only for latency statistics
Last checked2026-07-12 18:50 UTC+08
Last response852ms
1h p50 latency1.05s
1h p95 latency2.63s
24h p50 latency1.12s
24h p95 latency3.46s
Last errorNone

Gateway Load

cpa-public-proxy · Fresh 0s ago
Active Responses
4
oldest 13s
1h Peak Overlap
17
at 2026-07-12 18:16 UTC+08
1h Retry Attempts
10
slow requests 1,267
1h Proxy p95
57.15s
completed gateway requests
Owner-Workloadactive 1 · 1h requests 964 · retry 7
Public-Useractive 2 · 1h requests 460 · retry 3

Upstream Dependencies

OpenAI Status · Cached 60s
ResponsesOperational
Codex APIOperational
Codex WebUnknown
AgentOperational
  • Elevated conversation error rates on ChatGPT for iOS

Recent Checks

https://ai.tomandjerry2026.xyz/v1 / gpt-5.6-sol
  • Success852ms latency; HTTP 200; none
  • Success947ms latency; HTTP 200; none
  • Success789ms latency; HTTP 200; none
  • Success896ms latency; HTTP 200; none
  • Success952ms latency; HTTP 200; none
  • Success1.33s latency; HTTP 200; none
  • Success859ms latency; HTTP 200; none
  • Success1.39s latency; HTTP 200; none
  • Success910ms latency; HTTP 200; none
  • Success1.36s latency; HTTP 200; none
  • Success1.99s latency; HTTP 200; none
  • Success771ms latency; HTTP 200; none

Recent Events

Generated 2026-07-12 18:50 UTC+08
  • AvailabilityProbe recovered
  • AvailabilityProbe failed: server_error
  • AvailabilityProbe recovered
  • Probe DataStatus probe quota exhausted
  • AvailabilityProbe recovered
  • Probe DataStatus probe quota exhausted
  • AvailabilityProbe recovered
  • AvailabilityProbe failed: server_error