Incident with Grok Copilot AI Model Provider

Summary

Incident with Grok Copilot AI Model Provider

Between 13:22 and 17:11 UTC on September 03, 2026, GitHub Copilot experienced degradation affecting several Grok models, including Grok 4.5 and Grok 4.6. Users encountered elevated error rates, but other models were not affected. The degradation was caused by an issue with an upstream model provider. GitHub engineers detected the issue through automated monitoring, displayed in-product warnings for the affected models, and coordinated with the provider. Service returned to normal after the provider implemented a mitigation.

• Started

  Sep 3, 2026 · 2:17 PM

• Resolved

  Sep 3, 2026 · 5:11 PM

• Duration

  2h 54m

• Severity

  Minor

• ◐

  Investigating

  Sep 3 · 2:17 PM GitHub

  We are investigating reports of degraded performance for Copilot AI Model Providers

• ◐

  Investigating

  Sep 3 · 2:20 PM GitHub

  We are experiencing degraded availability for the Grok 4.6 model in Copilot Chat, VS Code and other Copilot products. This is due to an issue with an upstream model provider. We are working with them to resolve the issue.<br />

• ◐

  Investigating

  Sep 3 · 2:22 PM GitHub

  The Grok 4.5 model has degraded availability as well. We are working with the upstream provider to resolve the issue.

• ◐

  Investigating

  Sep 3 · 5:11 PM GitHub

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

• ✓

  Resolved

  Sep 3 · 5:11 PM GitHub

  Between 13:22 and 17:11 UTC on September 03, 2026, GitHub Copilot experienced degradation affecting several Grok models, including Grok 4.5 and Grok 4.6. Users encountered elevated error rates, but other models were not affected. The degradation was caused by an issue with an upstream model provider. GitHub engineers detected the issue through automated monitoring, displayed in-product warnings for the affected models, and coordinated with the provider. Service returned to normal after the provider implemented a mitigation.