Starting at 15:50 UTC on November 13, 2026, AWS Databricks experienced degraded availability for Claude Opus 5 and 5.5 models through Model Serving and AI Gateway, lasting approximately 1.6 hours. Affected customers encountered HTTP 503 errors, increased latency, and intermittent streaming failures, with downstream impact to Databricks Genie, Apps, and AI/BI. Claude Opus 5 recovered during mitigation efforts, with Opus 5.5 remaining impacted as the incident concluded.
Trusted by 1,000+ teams
Stop finding out about outages from your users. Monitor 6,320+ cloud services and get alerted the second something breaks.
Impact Summary
Starting at 15:50 UTC November 13, 2026, customers using Claude Opus 5 or 5.5 through Databricks may experience degraded availability with Model Serving. Affected customers may encounter failed or slow inference requests to certain foundation models served through Model Serving and AI Gateway. This could also adversely affect Databricks Genie, Apps, or AI/BI.
Symptoms
• Elevated error rates (HTTP 503) for foundation model API requests
• Increased latency for scoring requests
• Intermittent failures for streaming inference responses
Recommendations
Customers experiencing failed Claude Opus requests should retry with exponential backoff and, where possible, fall back to another model for critical workloads.
Current Status
The issue has been identified and mitigation efforts are in progress in coordination with the cloud provider.
Next Update
We will provide another update within 1 hour, or sooner if there is a material change in service status.
Impact Summary
Starting at 15:50 UTC November 13, 2026, customers using Claude Opus 5 or 5.5 through Databricks may experience degraded availability with Model Serving. Affected customers may encounter failed or slow inference requests to certain foundation models served through Model Serving and AI Gateway. This could also adversely affect Databricks Genie, Apps, or AI/BI. Opus 5 is currently recovered, leaving Opus 5.5 as the only model still seeing significant error rates.
Symptoms
• Elevated error rates (HTTP 503) for foundation model API requests
• Increased latency for scoring requests
• Intermittent failures for streaming inference responses
Recommendations
Customers experiencing failed Claude Opus requests should retry with exponential backoff and, where possible, fall back to another model for critical workloads.
Current Status
The issue has been identified and mitigation efforts are in progress in coordination with the cloud provider.
Next Update
We will provide another update within 1 hour, or sooner if there is a material change in service status.
With IsDown, you can monitor all your critical services' official status pages from one centralized dashboard and receive instant alerts the moment an outage is detected. Say goodbye to constantly checking multiple sites for updates and stay ahead of outages with IsDown.
Start free trialNo credit card required · Cancel anytime · 6320 services available
Integrations with