GCP Incidents

**Symptom** \ Customers experienced increased error rates when sending API requests to impacted multiple Gemini models through the global endpoint. 5/5

Preliminary analysis indicates the issue was triggered by a recent configuration change. Service was fully restored after the configuration change was rolled back. We thank you for your patience while we worked on resolving the issue 4/5

Low Multiple Products incident: Vertex AI Gemini API customers experienced increased error rates when accessing the global endpoint 1/5

@moisemorard sorry, I apologize

@GCP_Incidents @GCP_Incidents, stop to send old alerts please 🙏🏻

## ## \#\# Root Cause The service interruption was triggered by a procedural error during a planned hardware replacement in our datacenter 4/22

Duration:** 18 July 2025 07:50 \- 08:40 US/Pacific : 50 minutes We sincerely apologize for this incident, which does not reflect the level of quality and reliability we strive to offer We are taking immediate steps to improve the platform’s performance and availability 3/22

Medium Multiple Products incident: We are investigating elevated error rates with multiple products in us-east1 status.cloud.google.com/incidents/8cY8… ## \# Incident Report ## \#\# Summary On Friday, 18 July 2025 07:50 US/Pacific, several Google 1/22

## ## \#\# Root Cause The service interruption was triggered by a procedural error during a planned hardware replacement in our datacenter 4/22

Duration:** 18 July 2025 07:50 \- 08:40 US/Pacific : 50 minutes We sincerely apologize for this incident, which does not reflect the level of quality and reliability we strive to offer We are taking immediate steps to improve the platform’s performance and availability 3/22

Medium Multiple Products incident: We are investigating elevated error rates with multiple products in us-east1 status.cloud.google.com/incidents/8cY8… ## \# Incident Report ## \#\# Summary On Friday, 18 July 2025 07:50 US/Pacific, several Google 1/22

Cloud Platform (GCP) and Google Workspace (GWS) products experienced elevated latencies and error rates in the us-east1 region for a duration of up to 1 hour and 57 minutes **GCP Impact Duration:** 18 July 2025 07:50 \- 09:47 US/Pacific : 1 hour 57 minutes **GWS Impact 2/22

Cloud Platform (GCP) and Google Workspace (GWS) products experienced elevated latencies and error rates in the us-east1 region for a duration of up to 1 hour and 57 minutes **GCP Impact Duration:** 18 July 2025 07:50 \- 09:47 US/Pacific : 1 hour 57 minutes **GWS Impact 2/22

## ## \#\# Root Cause The service interruption was triggered by a procedural error during a planned hardware replacement in our datacenter 4/22

Duration:** 18 July 2025 07:50 \- 08:40 US/Pacific : 50 minutes We sincerely apologize for this incident, which does not reflect the level of quality and reliability we strive to offer We are taking immediate steps to improve the platform’s performance and availability 3/22

Medium Multiple Products incident: We are investigating elevated error rates with multiple products in us-east1 status.cloud.google.com/incidents/8cY8… ## \# Incident Report ## \#\# Summary On Friday, 18 July 2025 07:50 US/Pacific, several Google 1/22