Severe Latency Spike / Timeouts with Flagship Models over the Last 3 Days (Looping/Chunked Architecture via PHP)

Same for us - latency on the Responses API is extreme, and API calls seem to be silently stalling. We also have 900 sec time out on our heaviest API calls (JSON outputs) - and well over 50% of those are failing and having to be auto-reset. We received multiple reports from Open AI on 27 May (“Elevated Latency and Errors on API”) and that doesn’t seem to have been resolved - frustrating that the status page does not reflect this.