GitHub incident: Disruption with some GitHub services

Affected components

• Copilot AI Model Providers

1. resolvedSep 15, 2026, 11:17 UTC

   On September 15, 2026, between 05:45 and 09:50 UTC, the Claude Fable 5.1 model in GitHub Copilot experienced intermittently degraded availability, with an average error rate of 2.8%. During brief recurring 15 minute periods that recurred every ~45 minutes, availability for Claude Fable 5.1 dropped to a maximum of ~40% before recovering completely. Other Copilot models were not affected. Users could continue to work with a different model or with 'Auto'.<br /><br />The cause was an issue with an upstream model provider that intermittently rejected requests while overloaded. GitHub worked with the provider, who acknowledged and then resolved the underlying issue at 9:50 UTC, after which the model returned to constant normal availability. Once recovery was guaranteed, we resolved the incident at 11:17 UTC.<br /><br />To reduce the chance of recurrence and customer impact, GitHub is reviewing per-model availability alerting and automatic in-product fallback so that requests to a degraded m

2. investigatingSep 15, 2026, 11:17 UTC

   The issues with our upstream model provider have been resolved, and Claude Fable 5.1 is once again available in Copilot products and IDE surfaces.<br /><br />We will continue monitoring to ensure stability, but mitigation is complete.

3. investigatingSep 15, 2026, 11:09 UTC

   We continue to monitor intermittent errors affecting Claude Fable 5.1 in some Copilot products and integrated development environments. Customer-facing metrics have recovered, and we are awaiting confirmation from our upstream provider that the issue will not recur. Customers can select another model or Auto in the meantime.

4. investigatingSep 15, 2026, 10:32 UTC

   We continue to investigate intermittent errors affecting Claude Fable 5.1 in some Copilot products and integrated development environments. Customers can use another model or select Auto while we monitor the situation.

5. investigatingSep 15, 2026, 10:20 UTC

   Copilot AI Model Providers is experiencing degraded performance. We are continuing to investigate.

6. monitoringSep 15, 2026, 09:48 UTC

   We are investigating degraded availability for Claude Fable 5.1, affecting some Copilot products and integrated development environments. The issue is caused by a problem with our upstream model provider. Customers can use another model or select Auto while we investigate.

7. investigatingSep 15, 2026, 09:47 UTC

   We are investigating reports of impacted performance for some GitHub services.

What APIStatus.watch saw

• Sep 15, 2026, 10:25 UTCoperational → degraded
• Sep 15, 2026, 11:20 UTCdegraded → operational

Other services with incidents at the same time

Overlapping incidents aren't necessarily related.

• MongoDB Atlas: Impaired Cluster operations in AWS me-central-1 and AWS me-south-1Major · Sep 3, 2026, 16:44 UTC
• Elasticsearch: Elastic Agent enrollment/check-in failures on 9.5.3 (and 9.4.6) with Fleet remote Elasticsearch outputMajor · Sep 9, 2026, 20:44 UTC
• Anthropic: Intermittent error spikes for Claude Mythos 5.1 and Claude Fable 5.1Major · Sep 15, 2026, 09:48 UTC
• Twilio: Voice Call Failures from a Subset of Twilio Phone Numbers to Hong KongMinor · Sep 12, 2026, 00:16 UTC
• Grafana Cloud: Increased Execution Time for Browser Checks in Synthetic MonitoringMinor · Sep 15, 2026, 10:00 UTC

How often does GitHub have incidents?

GitHub reported 49 incidents in the last 90 days, 15 of them major or critical. A typical incident lasted 1h 16m. See GitHub's uptime and incident history