OpenAI

Elevated error rates across all services
Affected components
Labs
Updates

Write-up published

Read it here

Resolved

On Wednesday May 12 2023, from approximately 11:45am to 12:10pm GPT-3.5, GPT-3.5 Turbo and GPT-4 models were unavailable due to an incorrect deployment to our safety classifier configuration. Most customers started experiencing errors at 11:55am. After we detected an elevated error rate, we quickly rolled back the configuration change which restored service.

We have since fixed our tooling to catch these errors before they hit production. Also, we have added increased alerting to detect these errors more quickly to enable us to roll back faster. Lastly, we have a project already in progress to incrementally deploy changes, so that we can detect and revert errors while only running on a small percentage of traffic. That project will be operational within the quarter.

Fri, May 12, 2023, 12:03 AM

Resolved

This incident has been resolved.

Wed, May 10, 2023, 07:14 PM(1 day earlier)

Monitoring

The issue has been identified and we are currently investigating.

Wed, May 10, 2023, 07:12 PM

Investigating

We are currently investigating an issue affecting multiple services, including chat.openai.com, labs.openai.com, and API services.

Wed, May 10, 2023, 06:59 PM(12 minutes earlier)
Powered by

Availability metrics are reported at an aggregate level across all tiers, models and error types. Individual customer availability may vary depending on their subscription tier as well as the specific model and API features in use.