GitHub outage on August 24, 2026: Elevated errors on Fable 5 due to upstream provider
GitHub reported an incident affecting GitHub for 47 minutes on 24 August 2026, from 07:12 to 07:58 UTC.
Resolved
Official incident reported by GitHub
- Started
- 07:12
- 24 Aug 2026 UTC
- Resolved
- 07:58
- 24 Aug 2026 UTC
- Duration
- 47m
- 47 minutes
- Impact
- Major
- as rated by GitHub
- Updates
- 3
- posted by GitHub
Timeline
All times UTC.
Official incident from GitHub
Elevated errors on Fable 5 due to upstream provider
-
Official
Investigating
We are investigating reports of degraded availability for Copilot AI Model Providers
-
Official
Investigating
We are experiencing degraded availability for the Fable model in Copilot products and IDE surfaces. This is due to an issue with the upstream model provider. While we work with them to resolve the issue, we recommend choosing another model or selecting 'Auto' to continue using Copilot.
-
Official
Resolved
On August 24th, 2026, between approximately 06:35 and 07:25 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 when using Claude Fable 5, with requests sometimes failing mid-response. No other models were impacted. 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.
"Official" rows are quoted from GitHub's public status page, www.githubstatus.com. Very long posts are shortened.
What our checkpoints saw
HostTracker's checkpoints, which test github.com from several locations, recorded no outage of 5 minutes or longer during this incident. A provider can report a problem that affects only some features, regions or accounts, which a check of the main address does not see. The live GitHub status shows what our checks see right now.
Does your product depend on GitHub?
An outage like this one reaches your users through your product, and most teams hear about it from a customer rather than from a dashboard. HostTracker watches any endpoint you name - your own site, an API you call, a vendor you resell - from 300+ locations, confirms a failure from several of them before it says anything, and then tells you by email, SMS, voice call or your chat tool.
You get the same record you are reading here for your own services: every outage timestamped, with the checks that observed it.
Independent measurement by HostTracker. Not affiliated with GitHub. Official updates are quoted from GitHub's public status page and remain GitHub's own words.