‹ Back to incident history

Elevated errors on GPT-5.4 Nano

ResolvedMinor incidentGitHub
Tuesday, November 3, 2026 01:46 – Tuesday, November 3, 2026 02:24 (38 min)
Affected components
Copilot AI Model Providers
Updates
ResolvedTuesday, November 3, 2026 02:24

On November 2, 2026, between 17:30 and 18:10 UTC, background tasks such as generating commit messages in GitHub Copilot were degraded. This was due to elevated errors with GPT-5.4 nano, a utility model. The elevated errors originated from an issue with an upstream model provider. No models that users could pick in the model picker were impacted. Service recovered when the upstream provider released a fix. We are working with the provider to understand the root cause and prevent similar issues from occurring going forward.

MonitoringTuesday, November 3, 2026 02:10

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

InvestigatingTuesday, November 3, 2026 01:58

We are experiencing degraded availability for the GPT-5.4 Nano model in Copilot products and IDE surfaces. This is due to an issue with an upstream model provider.

InvestigatingTuesday, November 3, 2026 01:46

We are investigating reports of elevated errors on GPT-5.4 Nano

InvestigatingTuesday, November 3, 2026 01:46

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

Incident data from the GitHub official status page:Read the official incident

About this data

Where does the incident data for GitHub come from?

Data comes from the GitHub official status page, syncs every 5 minutes, and covers 90 days. The detail page links to the original report.

How do I read the component status bars?

Each block is one day. Green means no issue was reported, yellow means degraded performance, red means a major outage, and gray means no data. Availability covers the last 90 days.

Why is history missing for some services?

Only services with a public official status page are included.

How is duration calculated?

Duration runs from the official start time to recovery, or to the current time for ongoing incidents. Incidents spanning multiple days appear on each affected day.

See the full service list and live status in the status overview