New B200 spot capacity is live in US East from $1.69 per GPU-hour. See availability
Partial outage

API returning errors for all requests

The API was unavailable for 88 minutes. Running instances, the console and billing were not affected.

Reference b1ac5fa82f33 · Updated just now

Status
ResolvedResolved — last update 14 Aug 2025, 13:45 UTC
Started
14 Aug, 12:17Thursday 14 August 2025 UTC
Duration
1 h 28 minEnded 14 Aug 2025, 13:45 UTC
Components
1API
Timeline

What we posted, as we posted it.

Resolved4 updates · UTC
  1. ResolvedThis incident has been resolved. A post-incident review will be published here.14 Aug, 13:45
  2. MonitoringThe API has been serving normally since 13:18 UTC. We are monitoring and reviewing the change that caused this.14 Aug, 13:18
  3. IdentifiedA load balancer configuration push removed every API backend from the healthy pool. The previous configuration has been restored.14 Aug, 12:46
  4. InvestigatingThe API is returning 502 errors for most requests. Running instances are not affected. We are investigating.14 Aug, 12:17

Affected components

Details

Type
Partial outage
Started
14 Aug 2025, 12:17 UTC
Ended
14 Aug 2025, 13:45 UTC
Impact
The API was unavailable for 88 minutes. Running instances, the console and billing were not affected.
Reference
b1ac5fa82f33

Follow the Atom feed