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

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:

New Realtime Voice Models in the API Announcements

OpenAI announced a new generation of realtime voice models for the API: Advancing voice intelligence with new models in the API The release includes three new audio models for building more capable voice experiences: [realtime2] GPT-Realtime-2, a voice model with GPT-5-class reasoning for harder requests, better context handling, and more natural conversations. GPT-Realtime-Translate, a live translation model that supports speech from 70+ input languages into 13 output languages. GPT-Realti…