I believe OpenAI used Persona during the verification step that you must complete to use their SOTA models in the API. Not sure if it's still the case now.
Anyway, I found that too much of a hassle and switched to other LLM providers.
Anyway, I found that too much of a hassle and switched to other LLM providers.
A few months back I was evaluating one of the GPT-5 models for a side project. Turns out streaming via the API requires org verification, and I decided to look elsewhere.
In hindsight, a good decision given what just came out about Persona.