GPT‑Realtime‑2 not available via api private use error 4000

Anyone else getting this error? I would like to test it out for my voice applications. The release post says it is but I can’t seem to get it work.

Welcome to the forum!

I was able to call gpt-realtime-2, so it may not be a general outage.

Since it was just released, it could be access/rollout related, project/account specific or possibly the endpoint/model string being used.

If you keep getting the 400 error, I’d contact the Help Center: https://help.openai.com/en

Also, if you haven’t already, this announcement topic may be useful for more context around the GPT-realtime-2 release: