GPT-5.3 Codex is now available in Cursor!
It’s noticeably faster than 5.2 and is now the preferred model for many of our engineers.
I’m just starting to try 5.3, so I haven’t formed an impression yet. I think it’ll be better than 5.2-Codex.
What are your impressions of using Codex models in general? I’ve noticed that planning is better with just 5.2 High, and then coding with 5.*-Codex.
@Colin I can’t find this model, I’ve an enterprise sub. I can’t find any information about this so I’m wondering is this expected?
Some enterprises use allow/denylists for what models are available to their team. You should check with your team admins!