GroqCloud Console Errors Affecting Multiple Regions
We've mitigated the errors on the GroqCloud console and functionality has been restored. Inference API requests are not affected, and we will provide additional updates here.
We are currently investigating increased error rates on our GroqCloud console (including metrics, /models API endpoints, and API key creation). Users may receive 500 errors when making requests to console.groq.com. Our engineers are isolating the issue.
When: Monday, Nov 3, 2025 • 00:00 to 03:00 UTC (Sunday, Nov 2, 16:00 to 19:00 PT) What • We’re performing planned maintenance on the me-central-1 deployment of meta-llama/llama-4-maverick-17b-128e-instruct to keep systems current. Other regions remain available. Impact • No customer action required. • Requests that explicitly target the me-central-1 endpoint for this model will be unavailable for approximately 2 hours within the window, possibly longer if troubleshooting is required. • Requests not pinned to me-central-1 will continue to be served by other regions. Updates • We will post at start, after the change completes, and when monitoring finishes.
關於這些資料
Groq 的事件資料來自哪裡?
資料來自Groq 官方狀態頁,每 5 分鐘同步,保留最近 90 天。詳情頁提供官方記錄連結。
如何解讀元件狀態列?
每格代表一天。綠色表示無異常記錄,黃色表示部分降級,紅色表示較大故障,灰色表示無資料。可用率統計涵蓋最近 90 天。
為什麼有些服務查不到歷史?
只收錄提供公開官方狀態頁的服務。
持續時間如何計算?
按官方標記的開始至復原時間計算。進行中的事件計算至目前時間。跨天事件會顯示在每個受影響的日期。
完整的服務清單與即時狀態見狀態總覽