| Elevated errors on new model builds. Existing models are not affected (opens in new tab) | minor | 37 min |
| DeepSeek v4.1 outage on Model APIs. Dedicated Inference is not affected (opens in new tab) | major | 13 min |
| Elevated 500s in Single us-central Region (opens in new tab) | major | 13 min |
| Metrics degradation in UI and API. **Inference not affected** (opens in new tab) | minor | 21 min |
| Intermittent 5xx for a subset of models in 1 US Central cluster (opens in new tab) | minor | 1.4 h |
| Elevated inference 500s for a subset of models deployed in 1 US-East cluster (opens in new tab) | major | 42 min |
| Elevated inference 500s for a subset of models deployed in GCP central1 (opens in new tab) | major | 7 min |
| Metrics degradation in UI and API. **Inference not affected** (opens in new tab) | minor | 11 min |
| Kimi K3 Model API outage (opens in new tab) | major | 55 min |
| Elevated errors for models in a single India-based cluster (opens in new tab) | minor | 45 min |
| Partial outage on Kimi K3 model API inference (non-US only) (opens in new tab) | minor | 42 min |
| Partial outage on Nemotron Ultra Model API. **Dedicated Inference is not affected** (opens in new tab) | minor | 6 min |
| Elevated inference 500s for models in a single US-based cluster (opens in new tab) | major | 24 min |
| Elevated errors for models in a single US cluster due to provider outage (opens in new tab) | minor | 14 min |
| Elevated errors for deepseek-ai/DeepSeek-V4-Flash-0731 on Model APIs. **Dedicated Inference is not affected** (opens in new tab) | minor | 41 min |
| Elevated inference 500s for models in an EU cluster due to provider outage (opens in new tab) | minor | 41 min |
| Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected** (opens in new tab) | minor | 37 min |
| Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected** (opens in new tab) | minor | 1.3 h |
| Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected** (opens in new tab) | minor | 12 min |
| Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic on Model APIs. **Dedicated Inference is not affected** (opens in new tab) | minor | 48 min |
| Elevated errors for moonshotai/Kimi-K3 for US-pinned traffic (opens in new tab) | minor | 46 min |
| Metrics degradation in UI and API. **Inference not affected** (opens in new tab) | minor | 24 min |
| Elevated inference 502s for a subset of models in a single US cluster (opens in new tab) | minor | 43 min |
| Elevated inference 502s for a subset of models in a single US cluster (opens in new tab) | minor | 29 min |
| Slower than usual scale-ups for B200s (opens in new tab) | minor | 12 min |
| Elevated inference failures for models in an EU cluster (opens in new tab) | minor | 33 min |
| Slower than usual scale-ups in 1 us-central cluster (opens in new tab) | minor | 19 min |