alt Hacker NewsTry gpt-5.3-codex-spark - it's 1000 TPS and from my experience more capable than 5.4 mini.
If you have a subscription it's a different pool of usage.
Try gpt-5.3-codex-spark - it's 1000 TPS and from my experience more capable than 5.4 mini.
If you have a subscription it's a different pool of usage.
Used it, very fast but tiny context window and doesn't have good reasoning. (good for quick simple code changes)