What visitors reported during this incident
No visitor reports were filed for this incident.
Having problems with GitHub now? Check the current statusAffected services
Updates (6)
- Aug 31, 2026, 09:58 AMElevated rate of errors for OpenAI models provided by Copilot
Between 08:37 and 09:41 UTC on August 31, 2026, GitHub Copilot experienced degradation affecting several GPT models, including gpt-5.2, gpt-5.3-codex, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, and the gpt-5.6 family (Luna, Sol, and Terra). Users encountered elevated error rates and interrupted streaming responses. Other models were not affected.<br /><br />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 t
GitHub ↗ - Aug 31, 2026, 09:58 AMElevated rate of errors for OpenAI models provided by Copilot
The issues with our upstream model provider have been resolved, and gpt-5.3-codex, gpt-5.4-mini, gpt-5.4-nano, gpt-5.5, and the gpt-5.6 family of models are once again available in Copilot products and IDE surfaces.<br /><br />We will continue monitoring to ensure stability, but mitigation is complete.
GitHub ↗ - Aug 31, 2026, 09:51 AMElevated rate of errors for OpenAI models provided by Copilot
The degradation affecting Copilot AI Model Providers has been mitigated. We are monitoring to ensure stability.
GitHub ↗ - Aug 31, 2026, 09:48 AMElevated rate of errors for OpenAI models provided by Copilot
One of our model providers has confirmed an incident on their end. We have provided them details to help identify the issue. We are starting to see recovery.
GitHub ↗ - Aug 31, 2026, 09:22 AMElevated rate of errors for OpenAI models provided by Copilot
Copilot is experiencing a higher rate of errors for OpenAI models, including gpt-5.2, gpt-5.3-codex, gpt-5.4, gpt-5.4, and the gpt-5.6 family of models. Other models are not impacted. <br />
GitHub ↗ - Aug 31, 2026, 09:15 AMElevated rate of errors for OpenAI models provided by Copilot
We are investigating reports of degraded performance for Copilot AI Model Providers
GitHub ↗
What to do next
- Verify your own services recovered cleanly. Some upstream outages leave queues or caches in a degraded state, run smoke tests before declaring green internally.
- Save the post-mortem. Vendors usually publish a detailed RCA 1-3 days later. We'll add it to this page when it appears.
- Watch the provider going forward. Follow GitHub's status feed →
GlobalOutageMap aggregates publicly reported signals. We never claim authoritative status, always cross-check the provider's official channel before making business decisions.