Power has been fully restored and all capacity is back online at the facility. APIs have stabilized across all models that saw increased latencies and higher error rates.
Posted Mar 21, 2025 - 06:39 UTC
Update
We are actively working toward recovery on this incident
Posted Mar 21, 2025 - 03:40 UTC
Update
Our data center provider is actively working to restore power. The scope of potentially impacted models are deepseek-r1-distill-llama-70b, whisper-large-v3-turbo, llama-3.3-70b-versatile and llama-3.1-8b-instant. You may see error rates from the API when making requests to these models. Resolution TBD.
Posted Mar 20, 2025 - 17:58 UTC
Identified
The issue has been identified and a fix is being implemented.
Posted Mar 20, 2025 - 11:40 UTC
Investigating
A datacenter power issue is impacting the availability of several models. This issue is not expected to be fully resolved until later in the day 03/20/2025