API returning 500 errors intermittently on gpt-4o since this morning

Starting around 9am EST today, we're seeing intermittent 500 errors on gpt-4o completions. About 20% of requests fail.

Error response:

{
  "error": {
    "message": "The server had an error while processing your request.",
    "type": "server_error",
    "code": "internal_error"
  }
}

Our retry logic handles it but latency is way up. Is anyone else seeing this? The status page shows all green which is confusing.

Update: OpenAI confirmed the issue and it was resolved around 2pm EST.