Elevated rate of errors for OpenAI models provided by Copilot

What to do

• Check whether you use GitHub Copilot AI Model Providers. Check your stack

  Paste a package.json, lockfile, Terraform or a list of domains at down.guide/stack to see every provider you depend on.

• Confirm your retries, queues and scheduled jobs caught up after the 42m it lasted.

  Anything that failed between 2026-08-31 09:15 UTC and 2026-08-31 09:58 UTC may need a replay.

• Subscribe to GitHub's feed to hear about the next one first. RSS feed

  https://down.guide/feed?provider=github works in Slack (/feed subscribe), Discord feed bots and any RSS reader.

Updates from GitHub 6

1. investigatingAug 31, 2026, 9:15 AM UTC

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

   provider

2. investigatingAug 31, 2026, 9:22 AM UTC

   Copilot is experiencing a higher rate of errors for OpenAI models, including gpt-5.2, gpt-5.3-codex, gpt-5.4, gpt-5.4, and the gpt-5.6 family of models. Other models are not impacted.

   provider

3. investigatingAug 31, 2026, 9:48 AM UTC

   One of our model providers has confirmed an incident on their end. We have provided them details to help identify the issue. We are starting to see recovery.

   provider

4. monitoringAug 31, 2026, 9:51 AM UTC

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

   provider

5. monitoringAug 31, 2026, 9:58 AM UTC

   The issues with our upstream model provider have been resolved, and gpt-5.3-codex, gpt-5.4-mini, gpt-5.4-nano, gpt-5.5, and the gpt-5.6 family of models are once again available in Copilot products and IDE surfaces. We will continue monitoring to ensure stability, but mitigation is complete.

   provider

6. resolvedAug 31, 2026, 9:58 AM UTC

   Between 08:37 and 09:41 UTC on August 31, 2026, GitHub Copilot experienced degradation affecting several GPT models, including gpt-5.2, gpt-5.3-codex, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, and the gpt-5.6 family (Luna, Sol, and Terra). Users encountered elevated error rates and interrupted streaming responses. Other models were not affected. The degradation was caused by an issue with an upstream model provider. GitHub engineers detected the issue through automated monitoring, displayed in-product warnings for the affected models, and coordinated with the provider. Service returned to normal after the provider implemented a mitigation.

   provider

Corrections

None so far.

Something wrong on this page? Report an error or send us a note. Every fix is listed here.