Disruption with some GitHub services
Final update
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'. 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. 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 model can shift to a healthy alternative more quickly.
Timeline
- Resolved · Sep 15, 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'. 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. 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 model can shift to a healthy alternative more quickly.
- Investigating · Sep 15, 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. We will continue monitoring to ensure stability, but mitigation is complete.
- Investigating · Sep 15, 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.
- Investigating · Sep 15, 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.
- Investigating · Sep 15, 10:20 UTC
Copilot AI Model Providers is experiencing degraded performance. We are continuing to investigate.
- Monitoring · Sep 15, 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.
- Investigating · Sep 15, 09:47 UTC
We are investigating reports of impacted performance for some GitHub services.
More from GitHub
Full history| Started | Incident | Impact | Duration |
|---|---|---|---|
| Sep 2310:11 UTC | Incident across several services | minor | Ongoing |
| Sep 2022:13 UTC | Incident with Pull Requests | minor | 1h 9m |
| Sep 1720:59 UTC | Elevated rate of errors for OpenAI models provided by Copilot | minor | 50m |
| Sep 1607:20 UTC | Degradation with Gemini 3.8 Flash | major | 10h 28m |
| Sep 1519:11 UTC | Disruption with some GitHub services | minor | 49m |
| Sep 1418:40 UTC | Actions Larger Runner Jobs for some customers may be slow to start | minor | 55m |
Also caused by capacity and load
All| Started | Vendor | Incident | Impact | Duration |
|---|---|---|---|---|
| Sep 2213:19 UTC | We are investigating an issue with CH servers in Azure germanywestcentral region | minor | 5h 6m | |
| Sep 221:44 UTC | Elevated Linux worker queue times | minor | 21m | |
| Aug 2506:53 UTC | [Critical] Issue with Downloads | critical | 44m | |
| Aug 2015:40 UTC | We are investigating an issue where customers may experience timeouts, service degradations, errors, and elevated latencies across multiple products in the us-west1 region. | critical | 3h 40m | |
| Aug 1812:58 UTC | INC20000163 | major | 1h 54m | |
| Aug 1713:19 UTC | No capacity in ARN | none | 2h 22m |
From vendors' own status pages and disclosures. Times as reported. Logos via logo.dev; trademarks belong to their owners.