Is there a way to use the GPT-5.2 Pro model directly in Codex CLI?

Open 💬 7 comments Opened Jan 28, 2026 by Shuvomoy
💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

What feature would you like to see?

I recently subscribed to ChatGPT Pro plan, and for my specific coding tasks, the GPT-5.2 Pro model on the web interface performs very well. I have also tried the Codex CLI for the same problems, but the quality of its output is not as good as that of GPT-5.2 Pro.

I am unsure if there is a way to access the specific GPT-5.2 Pro model within the Codex CLI. The CLI offers gpt-5.2 and gpt-5.2-codex with reasoning levels ranging from Low to Extra High; however, I have found that even the 'Extra High' setting on these models is inferior to the web-based GPT-5.2 Pro for my use case.

Any tips/suggestions will be much appreciated.

Additional information

OS: Ubuntu
ChatGPT Plan: Pro

View original on GitHub ↗

7 Comments

github-actions[bot] contributor · 5 months ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

  • #9862
  • #9264
  • #10036

Powered by Codex Action

guidedways contributor · 5 months ago

@Shuvomoy there isn't - but you could create a custom _skill_ that creates a context.zip and a prompt.md for you to share with GPT 5.2 Pro via the ChatGPT app / interface.

etraut-openai contributor · 5 months ago

The GPT 5.2 pro model isn't recommended for coding use cases. It uses a "best of n" mechanism to produce results.

If you want high-reasoning code generation, we recommend using gpt-5.2 or gpt-5.2-codex with "xhigh" reasoning effort.

Shuvomoy · 5 months ago
@Shuvomoy there isn't - but you could create a custom _skill_ that creates a context.zip and a prompt.md for you to share with GPT 5.2 Pro via the ChatGPT app / interface.

Thanks so much for the tips @guidedways this is very useful. I will try that!

Shuvomoy · 5 months ago
The GPT 5.2 pro model isn't recommended for coding use cases. It uses a "best of n" mechanism to produce results. If you want high-reasoning code generation, we recommend using gpt-5.2 or gpt-5.2-codex with "xhigh" reasoning effort.

Okay, I will try that, thanks @etraut-openai !

vitarb · 5 months ago

I think we’re underestimating how powerful Codex would become if it could call GPT-Pro as a sub-agent.

That unlocks real Build Review loops, where Codex orchestrates and Pro plays the heavyweight designer or adversarial reviewer.

Right now I manually simulate this:

  • Session A: GPT-Pro scopes and drafts a design
  • Session B: GPT-Pro performs adversarial review
  • I paste B back into A for revision
  • Paste back into B
  • Repeat until the reviewer converges

The bottleneck is me. I’m mostly just shuttling outputs between sessions.

If Pro were callable as a skill inside a sub-agent, Codex could run this loop autonomously with explicit convergence or starvation criteria. You’d kick off a research loop, walk away, and come back to a refined, adversarially stress-tested design.

Think of this not as a coding mode, but more like a supercharged Plan mode, where codex will be able to design an entire new product from scratch.

seo-rii · 5 months ago
The GPT 5.2 pro model isn't recommended for coding use cases. It uses a "best of n" mechanism to produce results. If you want high-reasoning code generation, we recommend using gpt-5.2 or gpt-5.2-codex with "xhigh" reasoning effort.

Normally it's true, but pro can be useful in some case like program relies on mathematical strategies or requires very complex algorithm.

Like @vitarb said, calling pro model with collab(subagent) may be very useful. We don't need gpt-5.3-pro-codex. We just want to use existing pro model as subagent for planner, designer, etc.