Resolved after 10 hours 27 minutes, affecting Copilot AI Model Providers, on September 16, 2026.
On September 16, 2026, between 04:40 and 11:45 UTC, the Gemini 3.8 Flash model in GitHub Copilot experienced degraded availability. Requests to this model failed at an average rate of 6.4%, and the impact was highest during peak traffic hours. Other Copilot models were not affected. Users could continue to work with a different model or with 'Auto'. The degradation was caused due to a capacity issue with an upstream model provider. Failure rates returned to normal as the daily traffic peak passed. We monitored the model until it was healthy and resolved the incident at 17:48 UTC. We are working to make our systems resilient to cover peak demand for all the Copilot models.
Affected components
Update timeline
- investigating Sep 16, 2026, 07:21 AM UTC
We are investigating reports of degraded availability for Copilot AI Model Providers
- investigating Sep 16, 2026, 08:28 AM UTC
Copilot AI Model Providers is experiencing degraded performance. We are continuing to investigate.
- investigating Sep 16, 2026, 10:58 AM UTC
Copilot AI Model Providers is experiencing degraded performance. We are continuing to investigate.
- monitoring Sep 16, 2026, 11:45 AM UTC
The degradation affecting Copilot AI Model Providers has been mitigated. We are monitoring to ensure stability.
- resolved Sep 16, 2026, 05:48 PM UTC
On September 16, 2026, between 04:40 and 11:45 UTC, the Gemini 3.8 Flash model in GitHub Copilot experienced degraded availability. Requests to this model failed at an average rate of 6.4%, and the impact was highest during peak traffic hours. Other Copilot models were not affected. Users could continue to work with a different model or with 'Auto'. The degradation was caused due to a capacity issue with an upstream model provider. Failure rates returned to normal as the daily traffic peak passed. We monitored the model until it was healthy and resolved the incident at 17:48 UTC. We are working to make our systems resilient to cover peak demand for all the Copilot models.
Your product runs on more than GitHub
Add the vendors you depend on and get one message when any of them reports trouble. Free for 3 vendors, no card.
Amazon Web Services