GitHub Copilot incident: Errors with the Fable 5 Model in Copilot

Affected components

• Copilot AI Model Providers

1. resolvedAug 13, 2026, 15:47 UTC

   On August 13th, 2026, between approximately 14:06 and 15:47 UTC, the Copilot service experienced a degradation of the Claude Fable 5 model due to an issue with our upstream provider. Users encountered elevated error rates, peaking at 43% and averaging 12%. Users who selected Auto or alternative models were unaffected.<br /><br />The issue was resolved by a mitigation put in place by our provider. GitHub is working with our provider to further improve the resiliency of the service to prevent similar incidents in the future.

2. investigatingAug 13, 2026, 15:47 UTC

   The issues with our upstream model provider have been resolved, and Fable 5 is once again available in Copilot products and IDE surfaces.<br /><br />We will continue monitoring to ensure stability, but mitigation is complete.

3. investigatingAug 13, 2026, 15:23 UTC

   We are seeing modest recovery, but are still experiencing degraded availability for the Fable 5 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 'Auto' to continue using Copilot.

4. investigatingAug 13, 2026, 14:50 UTC

   We are experiencing degraded availability for the Fable 5 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 'Auto' to continue using Copilot.

5. investigatingAug 13, 2026, 14:43 UTC

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

What APIStatus.watch saw

Our 5-minute checks didn't record a change in GitHub Copilot's overall status around this incident. Smaller or regional incidents often leave a provider's overall status green.

Other services with incidents at the same time

Overlapping incidents aren't necessarily related.

• Shippo: Elevated error rate on ontrac Transaction APICritical · Aug 13, 2026, 12:51 UTC
• Shippo: Elevated error rate on lasership Transaction APICritical · Aug 13, 2026, 13:47 UTC
• Grafana Cloud: K6 Test OutageCritical · Aug 13, 2026, 15:25 UTC
• Elasticsearch: Increased error rates for microsoft-multilingual-e5-largeMajor · Aug 13, 2026, 08:32 UTC
• Anthropic: Elevated errors for Claude Mythos 5, Claude Fable 5, and Claude Sonnet 5Major · Aug 13, 2026, 14:33 UTC
• Cursor: Investigating service degradation — Automations, Cloud Agents, and IDEMajor · Aug 13, 2026, 14:46 UTC
• Twilio: IP Retrieval Failing for EU Regional CustomersMinor · Aug 10, 2026, 18:32 UTC
• Akamai: Certificate Provisioning System (CPS) IssuesMinor · Aug 11, 2026, 10:11 UTC
• Twilio: Voice Call Failures from a Subset of Twilio Phone Numbers to Multiple Networks in PeruMinor · Aug 12, 2026, 14:56 UTC
• Twilio: MMS Delivery Receipt Delays from a Subset of Twilio Short Codes to T-Mobile United StatesMinor · Aug 13, 2026, 13:19 UTC

How often does GitHub Copilot have incidents?

GitHub Copilot reported 15 incidents in the last 90 days, 5 of them major or critical. A typical incident lasted 1h 14m. See GitHub Copilot's uptime and incident history