What Changed

  • Google Cloud reported an incident causing increased error rates for Vertex AI Gemini API customers accessing the global endpoint, with a defined start time and subsequent resolution update [1].
  • No other primary artifacts or corroborating reports indicate lasting changes to Gemini model availability, rate limits, or capabilities following incident recovery [1].

Cross-Source Inference

  • Observed fact: Elevated error rates on the Vertex AI Gemini global endpoint during the incident window [1].
  • Inference: The disruption was transient and scoped to the global endpoint, with no persistent distribution impact, because Google’s status update indicates resolution and there are no concurrent official or downstream confirmations of follow-on restrictions or feature changes [1]. Confidence: medium (single primary source, no contradictions).

Implications and What to Watch

  • Short-term: Expect normal operations to continue; customers depending on the global endpoint may review regional endpoint failover strategies even absent official guidance [1].
  • Watch for: A Google postmortem detailing root cause, any mitigations, and whether guidance changes for endpoint selection or quotas emerge [1].
  • Monitor: Additional Google channels or customer reports that might indicate hidden regressions or rate-limit adjustments not captured in the initial status note [1].