Hello, all previous gpt models have low fast version, is there a reason 5.4 low fast is missing? is it on purpose?
Version: 2.6.19 (user setup)
VSCode Version: 1.105.1
Commit: 224838f96445be37e3db643a163a817c15b36060
Date: 2026-03-12T04:07:27.435Z
Build Type: Stable
Release Track: Early Access
Electron: 39.4.0
Chromium: 142.0.7444.265
Node.js: 22.22.0
V8: 14.2.231.22-electron.0
OS: Windows_NT x64 10.0.19045
Hey there!
The available model variants in the picker can vary — not all reasoning effort levels are shown for every model in every configuration. GPT 5.4 supports different effort levels, but the options in your picker may differ from what you see for other models.
Could you share which plan you’re on (Free, Pro, Pro+, Ultra)? That would help me narrow down why you’re seeing different options for 5.4 vs. previous GPT models.
Hello, Ultra.
Since you’re on Ultra, all model variants should be available to you.
You’re right that GPT 5.4 does support additional reasoning effort levels and speed variants – the model picker just isn’t showing all of them right now. This is a known gap we’re working to address – the team is actively expanding the options in the picker.
In the meantime, the variants you do see for GPT 5.4 (like High) should work well.
