Increased errors across API and ChatGPT

Write-up

At 11:46 AM PT on Nov 28, some OpenAI services experienced an increased error rate associated with a change to a production database. The issue was identified and at 11:57 AM PT normal operations resumed.

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.