Historical SLA

AI API Uptime History & Incident Log

Uptime, outages, degradations and time-to-resolve, computed from each vendor's published incident history. Major/critical incidents count as downtime; minor ones as degradation.

OpenAI

99.446%

Incidents
7
Outages
1
Downtime
56 min
Degraded
57.1 h
Mean time to resolve
4.0 h

Claude / Anthropic

98.753%

Incidents
1
Outages
1
Downtime
2.1 h
Degraded
0 min
Mean time to resolve
2.1 h

Perplexity

100.000%

Incidents
0
Outages
0
Downtime
0 min
Degraded
0 min
Mean time to resolve
—

OpenRouter

100.000%

Incidents
0
Outages
0
Downtime
0 min
Degraded
0 min
Mean time to resolve
—

GitHub / Copilot

99.487%

Incidents
3
Outages
1
Downtime
52 min
Degraded
3.8 h
Mean time to resolve
1.6 h

Cloudflare Workers AI

100.000%

Incidents
17
Outages
0
Downtime
0 min
Degraded
89.1 h
Mean time to resolve
2.8 h
As of: Oct 1, 2026, 12:44 PM UTCSource: Providers' public Statuspage status and incident feeds Method: Major and critical incident duration counts as downtime; minor and informational incident duration counts as degraded time. Uptime is Token Terminal's derived observation, not a provider-certified SLA.

Incident audit log · last 7 days

Get paged when this happens — alerts can go to email, Slack, Discord, PagerDuty or Opsgenie.

Set up alerts
Help