System Status
All Systems Operational
Last updated:
90-Day Uptime
Last 90 days
Last 90 days
Last 90 days
Last 90 days
Service Components
| Component | Status | Uptime (30d) | Response Time |
|---|---|---|---|
| API Endpoint | Operational | 99.8% | ~120ms |
| Authentication | Operational | 99.9% | ~50ms |
| DeepSeek Models | Operational | 99.5% | ~800ms |
| Qwen Models (Alibaba) | Operational | 99.9% | ~600ms |
| SiliconFlow Models | Operational | 99.6% | ~700ms |
| Embedding Models | Operational | 99.7% | ~200ms |
| Vision Models | Operational | 99.4% | ~1200ms |
| Streaming (SSE) | Operational | 99.7% | ~50ms TTFB |
Recent Incidents
Jul 20, 2025 • Duration: 15 minutes
Some users experienced increased latency (2-5x) when using models routed through SiliconFlow. Root cause was a network routing issue at the provider level. The issue resolved automatically. We've implemented additional monitoring to detect such issues faster.
Jul 18, 2025 • Duration: 45 minutes
The GLM-5.2 model experienced timeouts due to upstream capacity constraints at Zhipu AI. Users were automatically routed to alternative models during this period. GLM-5.2 service was fully restored after the provider scaled their infrastructure.
Jul 10, 2025 • Duration: 30 minutes (planned)
We performed a scheduled upgrade to our API gateway infrastructure to improve performance and reliability. During the maintenance window, some requests may have experienced brief interruptions. All systems were operational after the upgrade.
Uptime History (Last 14 Days)
Follow us on Telegram for real-time status notifications and incident updates.