Realtime API Session Timeout (Post GA)

Since the Realtime API has moved to GA, has there been an update to the session limit increasing it from 30 minutes?

up to 60 minutes

see Developer notes on the Realtime API

  • Realtime sessions can now last up to 60 minutes, up from 30 minutes.

  • The gpt-realtime model has a token window of 32,768 tokens. Responses can consume a maximum of 4,096 tokens. This means the model has a maximum input of 28,672 tokens.

1 Like

Is there anyway to limit it from my backend when I am creating ephemeral token?
I want to limit my client to use base on their token limits