The last few days I’ve been seeing extremely long queued responses in the responses API. Even on low or none reasoning level I am occasionally seeing replies take over 5 minutes, sometimes 10+ minutes. Originally I saw this on GPT 5.4, but also it’s happening occasionally on 5.5. I originally thought this was on my end, but after some additional logging I’ve found it is in fact occurring on the OpenAi side.
Has anyone else seen this?
Hi @bejmorri,
Thank you for reporting this and for sharing the additional details from your logging. The team is actively investigating this.
You can follow the latest updates on the status page here:
Will be sharing updates as they become available.
You can also subscribe to live updates for this incident by pasting the following text into the slack channel of choice:
/feed subscribe https://status.openai.com/incidents/01KRP6FM6HSKWB3MS1EJTY6AT4/slack.rss
Hey @bejmorri! Yeah, I can see how that would be frustrating, especially with requests sitting queued for 5–10+ minutes.
What @sps shared is the right place to track this. There was a GPT5.5 performance degradation incident reported on May 15, mitigation was applied on May 16, and the status page now shows all impacted services have fully recovered.
For future updates on service issues, you can follow along on status.openai.com. If you continue to experience the issue, please let me know and I’ll be happy to take a look.
- Sunny