GitHub Status · History · Incident #138411

RESOLVED

Elevated rate of errors for OpenAI models provided by Copilot

Minor · Started Sep 17, 2026 · 8:59 PM

  • Duration

    49m

  • Severity

    Minor

  • Detection lead

  • User reports

Summary

Elevated rate of errors for OpenAI models provided by Copilot

Between 20:26 and 21:17 UTC on September 17, 2026, GitHub Copilot experienced degradation affecting several GPT models, including GPT-5.6 Luna, GPT-5.6 Terra, GPT-5.6 Sol, GPT-5.3-Codex, and GPT-6 Astra. Users encountered elevated error rates when using these models.<br /><br />The degradation was caused by an issue with an upstream model provider. GitHub engineers detected the issue through automated monitoring and coordinated with the provider. Our automated model-warning system activated in-product warnings for affected models during the incident. Service returned to normal after the provider implemented a mitigation.


  • Started

    Sep 17, 2026 · 8:59 PM

  • Resolved

    Sep 17, 2026 · 9:49 PM

  • Duration

    49m

  • Severity

    Minor

Event timeline

How this incident unfolded

  • Investigating

    Sep 17 · 8:59 PM GitHub

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

  • Monitoring

    Sep 17 · 9:39 PM GitHub

    We are experiencing degraded availability for GPT-5.6 Luna, GPT-5.6 Terra, GPT-5.6 Sol, GPT-6 Astra, GPT-5.3-Codex in Copilot products and IDE surfaces. This is due to an issue with an upstream model provider. The provider is working to mitigate the problem and we are monitoring recovery. We recommend choosing another model or selecting 'Auto' to continue using Copilot.

  • Resolved

    Sep 17 · 9:49 PM GitHub

    Between 20:26 and 21:17 UTC on September 17, 2026, GitHub Copilot experienced degradation affecting several GPT models, including GPT-5.6 Luna, GPT-5.6 Terra, GPT-5.6 Sol, GPT-5.3-Codex, and GPT-6 Astra. Users encountered elevated error rates when using these models.<br /><br />The degradation was caused by an issue with an upstream model provider. GitHub engineers detected the issue through automated monitoring and coordinated with the provider. Our automated model-warning system activated in-product warnings for affected models during the incident. Service returned to normal after the provider implemented a mitigation.

Get alerted before the next GitHub outage.

Pulsetic catches degradations minutes before vendors acknowledge them.