# Degraded Availability for MAI Code 2 Flash in Copilot

> Source: <https://www.githubstatus.com/incidents/891rm8181xdf>
> Published: 2026-11-18 09:34:15+00:00

**Recommendation:** Configure a fallback model or routing option for any Copilot-integrated model so users keep working when an upstream provider degrades, as Microsoft did with Copilot Fusion.
More in the playbook "Running AI in production": <https://wpnews.pro/playbooks/production-ops>

Nov `18`, `09:34` UTC

 **Resolved** - 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. 

 Nov `18`, `09:34` UTC

 **Update** - The issues with our upstream model provider have been resolved, and MAI Code 2 Flash is once again available in Copilot products and IDE surfaces.

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

 Nov `18`, `09:13` UTC

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

 Nov `18`, `09:13` UTC

 **Update** - We have been working with the upstream provider and applying mitigations, and are seeing widespread improvement in availability for MAI Code 2 Flash across Copilot products and IDE surfaces.

We will continue monitoring. 

 Nov `18`, `09:00` UTC

 **Update** - We are experiencing degraded availability for the MAI Code 2 Flash model in Copilot products and IDE surfaces. This is due to an issue with an upstream model provider. While we work with them to resolve the issue, we recommend choosing another model or selecting ‘Copilot Fusion’ to continue using Copilot. 

 Nov `18`, `09:00` UTC

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