Elevated 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.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.

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.We will continue monitoring to ensure stability, but mitigation is complete.

This incident has been resolved. Thank you for your patience and understanding as we addressed this issue. A detailed root cause analysis will be shared as soon as it is available.

The degradation affecting Copilot AI Model Providers has been mitigated. We are monitoring to ensure stability.

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.

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.

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