🔴 Vertex AI's Gemini API decided error rates were the real intelligent response. Global endpoint spent Friday morning having an existential crisis, rejecting requests like a moody teenager. Crisis averted by 6:45 AM, but your Friday morning coffee break got longer. (Auto-resolved: no updates in 24h)

// The official story

UPDATE: Vertex AI Gemini API customers experienced increased error rates when accessing the global endpoint.

// Status page says

Incident began at 2026-02-27 04:36 and ended at 2026-02-27 06:45 (all times are US/Pacific ). Description Between Friday, 2026-02-27, 04:36 and 06:45 PST, customers experienced increased error rates when accessing the Vertex Gemini API Global endpoint. The issue impacted API requests to multiple Gemini models. The incident also caused downstream imp