editing model after writing the prompt

Resolved 💬 3 comments Opened May 21, 2026 by goyalayus Closed May 21, 2026

💡 Likely answer: A maintainer (etraut-openai, contributor) responded on this thread — see the highlighted reply below.

What variant of Codex are you using?

CLI

What feature would you like to see?

currently /model only works in an empty input box. it should work in between writing prompts, becuase sometimes we realise after writing the prompt that this can be done by a faster model

Additional information

_No response_

View original on GitHub ↗

3 Comments

etraut-openai contributor · 3 months ago

You can change the /model any time between turns. A turn starts when you issue a prompt and ends when the model stops working on that turn.

If you want to change the model in the middle of a turn, you need to cancel the current turn (Ctrl+C).

goyalayus · 3 months ago

no i meant changing it while writing the prompt, sometimes i have written a
paragraph long prompt and then i realize i have to change the model

the ideal solution would be to be able to go at the start of prompt and
write /model

and then when we hit enter, first model changing prompt comes then the
request executes

On Thu, May 21, 2026 at 9:37 PM Eric Traut @.***> wrote:

Closed #23859 <https://github.com/openai/codex/issues/23859> as not planned. — Reply to this email directly, view it on GitHub <https://github.com/openai/codex/issues/23859#event-25813312795>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/A4ULSIUA7HXUPHIGBK4KAKL434SSZAVCNFSM6AAAAACZHRF73KVHI2DSMVQWIX3LMV45UABCJFZXG5LFIV3GK3TUJZXXI2LGNFRWC5DJN5XDWMRVHAYTGMZRGI3TSNI> . Triage notifications on the go with GitHub Mobile for iOS <https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android <https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>. You are receiving this because you authored the thread.Message ID: @.***>

etraut-openai contributor · 3 months ago

Ah, thanks for the clarification.

Here's a pro tip: If you have a prompt partially typed, you can use Ctrl+C to clear and stash that prompt, then use /model to change the model. Then use the up arrow to restore the previous (stashed) prompt.