Databricks: ES-2359687
Affected components: AI/BIDatabricks AppsGenie
Timeline of updates
- identified
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.
- identified
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.
- monitoring
Impact Summary Between 15:50 UTC and 21:25 UTC on November 13, 2026, customers using Databricks may have experienced degraded performance with AI/BI, Databricks Apps, Model Serving, and Genie. Affected customers may have encountered intermittent errors, timeouts, or elevated latency when sending requests to foundation models during this window. Symptoms • Foundation model serving requests returning errors or timing out • Elevated response latency for model inference and generated answers • Genie and AI/BI conversational analytics prompts failing or not completing Current Status The issue has been mitigated in coordination with the cloud provider, and service is operational. Next Update We will provide another update within 1 hour, or sooner if there is a material change in service status.
- resolved
Impact Summary Between 15:50 UTC and 21:25 UTC on November 13, 2026, a subset of customers using Databricks may have experienced degraded performance with AI/BI, Databricks Apps, Model Serving, and Genie. Affected customers may have encountered intermittent errors, timeouts, or elevated latency when using foundation model requests and AI-powered experiences during this window. Symptoms • Intermittent errors or failures for foundation model serving requests • Elevated latency or timeouts for Genie and AI/BI conversational analytics responses • Errors or degraded responsiveness in AI-powered features within Databricks Apps Current Status The issue has been resolved, and all affected services have been restored. Next Update This is the final update for this incident. We apologize for any inconvenience this may have caused. If you require further details about this incident, please submit a support ticket or contact help@databricks.com.
Changes Rewindex caught on this incident
- Major incident: ES-2359687
- Incident updated: ES-2359687
- Incident updated: ES-2359687
- Incident updated: ES-2359687
Archive proof
Rewindex commits each version of an incident it captures to a daily checkpoint, chains it to the day before, and has the checkpoint timestamped by FreeTSA and DigiCert. That proves these records existed by then and have not been changed since, by anyone, Rewindex included.
How the archive is checked, and what it cannot prove.
First version captured
In the 2026-11-13 checkpoint, timestamped by FreeTSA and DigiCert on . Record hash
83ccd6ccac876946…Version 2 captured
In the 2026-11-13 checkpoint, timestamped by FreeTSA and DigiCert on . Record hash
626aab112cc9e7be…Version 3 captured
In the 2026-11-13 checkpoint, timestamped by FreeTSA and DigiCert on . Record hash
0dcf2e682a10e176…Version 4 captured
In the 2026-11-13 checkpoint, timestamped by FreeTSA and DigiCert on . Record hash
4a53833e9ea9896f…
Impact, status and times are the vendor’s own, as last archived. View on status.databricks.com (opens in new tab).
Cite this
Status incident (vendor impact label: major) posted by Databricks, started 2026-11-13 20:13 UTC, resolved after 2.9 h, 4 update(s); edited after publishing.
- Title
- ES-2359687
- Vendor
- Databricks
- Date
- URL
- https://rewindex.com/company/databricks/incidents/6af76f66fb71f5042f7d9699
Databricks profileRecent Databricks incidentsAll outages on November 13, 2026Databricks in November 2026MarkdownJSON