Services
API Gateway
Primary routing endpoint
Operational
18ms
99.98%
Model Routing
Intelligent provider selection
Operational
5ms
99.99%
Authentication
API key validation & auth
Operational
12ms
100%
Dashboard
Web UI & analytics
Operational
45ms
99.95%
Webhooks
Event delivery
Operational
—
99.97%
90-Day Uptime
99.97% average
Operational
Degraded
Incident
Incident History
Elevated latency on API Gateway
Resolved
Mar 22, 2026
A misconfigured load balancer caused P99 latency to spike to ~800ms for approximately 23 minutes. No requests were dropped. Root cause identified and corrected. Post-mortem published internally.
Partial Anthropic model unavailability
Resolved
Mar 8, 2026
Anthropic experienced an upstream outage affecting Claude models for ~45 minutes. Our fallback routing automatically redirected affected requests to OpenAI models. Users with strict model pinning experienced errors; automatic retry logic resolved 94% without user intervention.
Authentication service degradation
Resolved
Feb 17, 2026
A database connection pool exhaustion caused token validation failures for approximately 8 minutes during a traffic spike. All failed requests returned 401 errors. Connection pool limits have been increased and auto-scaling thresholds adjusted.