Fireworks AI: Service Degradation for Deepseek V4.1 Flash
Fireworks AI experienced a service degradation affecting Deepseek V4.1 Flash. The incident has since been resolved and the service is operational.
– UTC
Here's why. Incidents from Wednesday, October 14, 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.
12 outages, 2 still active today. Worst: Prisma (35 d 12 h).
Fireworks AI experienced a service degradation affecting Deepseek V4.1 Flash. The incident has since been resolved and the service is operational.
– UTC
Fireworks AI experienced a service degradation affecting the GLM 5.3 Fast model. The incident has been resolved and the service is fully operational again.
– UTC
Since approximately 14:00 UTC, macOS jobs using Xcode 26.6.0 on the M4 Pro large resource class have experienced delays starting, with wait times reaching up to 30 minutes. The issue has been resolved since 15:11 UTC.
– UTC
The OpenAI service experienced limited availability for its gpt-image-2.5-flare and gpt-image-2.5-sunburst components, affecting image generation functionality. The issue has been resolved.
– UTC
Codex in the ChatGPT Desktop service experienced degraded performance, while the ChatGPT Work service was unaffected. The issue has been resolved.
– UTC
On October 13, GitHub Actions experienced a delay in showing logs for workflow runs. No logs were lost and the issue has been resolved with log processing catching up.
– UTC
A production outage occurred on GitLab, affecting users during a rate limit preview feature. No specific affected versions or workarounds were provided.
since
Fireworks AI experienced a service degradation affecting the GLM 5.3 model. The incident has since been resolved and the service is fully operational.
– UTC
A latency issue affecting the Realtime component of Supabase was resolved. No affected versions or workarounds were provided.
– UTC
The upgrade to prisma v8.0.0-rc.18 introduced breaking changes, including issues with raw SQL literals and PSL index expressions. The app recipe ships a script that rewrites every .prisma file, affecting users who upgraded.
since
Increased errors and latency observed in login and viewing packages on npmjs.com. The issue is currently being monitored after a fix has been implemented.
– UTC
An issue with data ingestion into Elastic APM for the EU region has been identified and resolved. The problem is currently under monitoring to ensure there are no lingering issues.
– UTC