MicrosoftRadarIndependent status for Microsoft services

Degradation with Gemini 3.8 Flash

ResolvedResolved1 version

Facts

Source
GitHub Status · original
Started
(58 days ago)
Ended
· lasted 10 h 28 min
How it ended
Microsoft marked it resolved.
First captured by us
Last changed
(43 min ago)
Affected services
GitHub Copilot AI model providers

Last text from Microsoft

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'.<br /><br />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.

Quoted from GitHub Status (source), captured . Reproduced for reporting and archival purposes.

Official updates

Posted by GitHub Status, newest first.

  1. Resolved

    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'.<br /><br />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.

  2. Monitoring

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

  3. Investigating

    Copilot AI Model Providers is experiencing degraded performance. We are continuing to investigate.

  4. Investigating

    Copilot AI Model Providers is experiencing degraded performance. We are continuing to investigate.

  5. Investigating

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

What Microsoft changed

Microsoft edits the text of an incident in place. We keep every version we capture (checked every minute) and highlight the difference. Removed text is struck through, added text is marked.

  1. First version we captured

    Captured · Microsoft's own timestamp · revision dkg6ntmq
    Original text as we first saw it

    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'.<br /><br />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.