Cloudflare Production Outage
A major production outage affecting all users of the Cloudflare service, resulting in a loss of functionality and user frustration.
since
Here's why. Incidents from Thursday, October 15, 2026 (UTC), ranked byBreakage Velocity.What is Breakage Velocity?A live score of how fast an outage or regression is spreading. The more people hit it, and the faster, the higher it climbs; it cools off as things calm down.Open-ended scale: under 25 low · 25+ elevated · 100+ high · 300+ extreme.
14 outages, 5 still active today. Worst: Cloudflare (34 d 13 h).
A major production outage affecting all users of the Cloudflare service, resulting in a loss of functionality and user frustration.
since
The Hugging Face Transformers API experienced a rate limit issue, causing an elevated number of 429 responses. This affected users who were making excessive requests to the API.
since
GitLab.com is experiencing delays in CI/CD pipelines, with some jobs remaining in the created state for an extended period or failing to start. More details available at <https://gitlab.com/gitlab-com/gl-infra/production/-/work_items/23234>.
– UTC
GitHub's CCA (Continuous Compliance Automation) experiences delays when users start an Automation, causing performance issues. The issue has been resolved after investigation.
– UTC
The OpenAI API experienced a widespread feature degradation affecting login functionality. The issue has been resolved.
– UTC
Between 06:40 and 09:50 UTC, errors occurred in creating apps and managing secrets. Running apps and machines were not affected.
– UTC
Fireworks AI experienced a service degradation affecting the Qwen 3.8 Max model. The incident has been resolved and the service is now fully operational.
– UTC
Fireworks AI experienced a service degradation affecting Kimi K3. The incident has been resolved and the service is now fully operational.
– UTC
GitLab.com is experiencing HTTP 500 errors on some pages, affecting the ability to sync groups with customers.gitlab.com. GitLab.com itself remains unaffected.
– UTC
Fireworks AI experienced a service degradation affecting Kimi K3, resulting in operational issues. The incident has since been resolved and the service is fully operational.
– UTC
Fireworks AI experienced an outage impacting multiple serverless models including GPT-OSS, Nemotron, GLM, Deepseek, MiniMax, and Qwen. Service has since been restored and all affected components are operational.
– UTC
DeepSeek experienced an outage affecting all users, with no specific version mentioned. The incident resulted in a production-level issue.
since