I noticed the gpt-4o-mini-realtime is not available anymore in the playground. And I have a production app using it, it is unclear to me if it will be continued to be supported on the webrtc api??
Also, 4o-mini-realtime is a better model than 4o-realtime, because 4o-realtime annoyingly talks slower like a doped AI and is way more expensive.
@OpenAI_Support I don’t know how you guys are going to build trust among developers for using your tech while nothing seems reliable and gpt models are becoming systematically lazy!? An intelligent model that is lazy is not a useful model to do serious work. It saddens me seeing how openai is falling behind
The gpt-4o series are the only “talking” AI models.
Both gpt-4o-realtime and the mini version are currently a “preview”, whatever that means, and both have the same latest version date. There is no reason to suspect one is going away.
Check your selected API project and any model enabling or disabling that can be done within, as the model is there:
Is there going to be a production (GA) release of the realtime mini model? I would have expected to see gpt-mini-realtime alongside gpt-realtime being released. Why is that not the case?
Also, the openAI pricing page (https://openai.com/api/pricing/) shows GPT-4o mini incorrectly under realtime audio which is blatantly incorrect. I tried and as expected it responds with “Model GPT-4o mini is not supported in realtime mode. See https://platform.openai.com/docs/models for a list of supported models “
