Inference API
- 24h API availability
- 100.00%
- 24h all models healthy
- 100.00%
- Last probe
- Slowest origin, p50
- 134 ms
- Slowest origin, p95
- 603 ms
- Full probe sweep, p95
- 915 ms
Models
| Model | State | 24h |
|---|
| deepseek-ai/deepseek-v4.1-flash | serving | 100.00% |
Incident note
No incident note posted.