outages.live
Live
GitHubIncident ·

Copilot experiencing degraded model availability for some GPT models

DegradedOfficial update
0

GitHub Copilot has degraded availability for the GPT models gpt-5.6-sol-fast, gpt-5.6-sol, gpt-6.1-terra, and gpt-6-luna. This issue affects the Copilot AI Model Providers component in Copilot products and IDE surfaces. GitHub reports that the problem comes from an upstream model provider, and the status is investigating. GitHub recommends choosing another model or selecting Auto to continue using Copilot.

State

Investigating

Started

Ongoing for

29 min

Worst impact

Degraded

Timeline

1 update
20:1320:2120:2820:3520:43
DegradedUpdate postedTimes in UTC

Investigating

29 min 100%

Updates

Times in UTC

As posted by GitHub

Investigating

We are experiencing degraded availability for gpt-5.6-sol-fast, gpt-5.6-sol, gpt-6.1-terra, and gpt-6-luna 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 'Auto' to continue using Copilot.

Affected components

1
Copilot AI Model Providers

GitHub in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

67

Days with an incident

45

Median duration

1 h 16 min

This incident

61% shorter than the median

How long each incident lasted, on the day it started. The outlined bar is this incident.

20 h 7 min
median 1 h 16 min
90 days agoToday

Other GitHub incidents

All incidents

GitHub·Incident with Pull Requests

GitHub Pull Requests had degraded availability. Some merge attempts timed out. GitHub reported the incident as resolved. The incident lasted about 2 hours and 42 minutes.

Resolved

GitHub·Disruption with Email Delivery

GitHub email delivery did not work for account sign-in, new account sign-up, email address verification, password resets, and email notifications. GitHub reports that the incident is resolved and that it lasted 2 hours and 7 minutes.

Resolved · 1 affected

GitHub·Incident with Webhooks API

GitHub Webhooks API had timeouts and errors that affected about 1% of customer traffic. GitHub mitigated the degradation and monitored stability. The incident is resolved and lasted about 51 minutes.

Resolved

GitHub·Impact across multiple GitHub products including Actions, Pages, and Copilot products.

GitHub reports a major outage that affected Webhooks, Actions, Pages, and Copilot. GitHub later reported recovery across all services and monitored the fix. GitHub marked the incident resolved. The outage lasted 33 minutes.

Resolved

GitHub·Incident with Webhooks

GitHub Webhooks had degraded performance. GitHub reports that the incident is resolved. The outage lasted 4 minutes.

Resolved

Follow GitHub

Your coding agent knows when GitHub is down, and tells you when a failure is theirs, not yours. You can also get GitHub incidents in a feed reader or in Slack.

Prompt
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.

Add it as a remote MCP server named "outages" at https://outages.live/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.

Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "github" and tell me if GitHub has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.

Paste this into any coding agent. It adds the server with its own MCP setup.

RSS
https://outages.live/feed.xml?providers=github
Slack
/feed subscribe https://outages.live/feed.xml?providers=github

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane