Can you add the "use gpt-5" option again?

[rahulgautama97-2599 (Vani)]

• It is superior to md and lg models in getting my task done.

• It has more contextual understanding of my project too.

• It is cheaper per prompt as well.

• Using gpt-5 gave me a euphoric feeling that I would never have to look at code again. Now I’m correcting issues from md model yet again.

• It hurts me adding this at the end of prompt every time “-dont’ change existing functionality -if you have any questions then ask. don’t hallucinate etc etc (busness secrets )“

  But seriously. Please provide gpt-5 again.

[system]

Did you know there’s another category dedicated to v0 topics? A human should be here soon to help, but the answer may already be available even faster in one of these other posts.

Our docs are a great place to start.

What is v0? | v0 Docs

We also have a walkthrough to help guide your workflow.

Become a v0 expert

Getting Started Using v0 is like chatting with a frontend engineer, who takes in your design guidelines and creates an application for you. A common workflow with v0 is putting in design files and images to scaffold your application and then use text prompts to nudge v0 into creating your perfect application. Remember, just like any other AI tool, the quality of the output that v0 generates depends on the quality of the prompt or instructions you input. So, it’s important to be clear, descripti…

And these recordings can give you a look at v0 features and strategies in action shown by our Community:

https://community.vercel.com/tags/c/events/42/v0

[pawlean (Pauline P. Narvas)]

Hi, Vani! Welcome to the Vercel Community

Have you seen our new agent mode?

Community Session: v0.dev is now v0.app

[Community Session: v0 announcement] Join the v0 team for a product announcement. To join in the live chat - join the community and click “Going” above Speakers [Alli Pope] [Esteban Suárez] Alli Pope Ary Khandelwal Partnerships Lead, v0 and Startups Product Manager, v0 X | LinkedIn X | LinkedIn Moderators [Pauline P. Narvas] Pauline Narvas (@pawlean) Community X | LinkedIn | Bluesky

Agent mode feedback thread

v0 has just launched Agent mode which adds task list creation queued messages looking up docs for libraries you mention automatic model selection for tasks and subtasks The automatic model selection means v0 can use a different model for reasoning than it uses for planning and again a different model for actually generating the code. For example it might pick GPT 5 for planning or design tasks and then switch to v0-1.5-md to reliably output the code For this reason the model selector and t…

[rahulgautama97-2599 (Vani)]

Yes I have. But gpt-5 was inherently better at the job.

I’ll reiterate the reasons

• contextual awarness
• getting the job done
• CHEAPER
• less silly mistakes
• exponentially less hallucination

can you let me use gpt-5 ONLY? I woudl prefer working with it exclusively. An option to let the users choose their preference would be better. The Agent placeholder doesn’t give me option to select the model like it used to before.

`The automatic model selection means v0 can use a different model for reasoning than it uses for planning and again a different model for actually generating the code. For example it might pick GPT 5 for planning or design tasks and then switch to v0-1.5-md to reliably output the code`

Again, my preference is with gpt-5. please let me use it exclusively.

[pawlean (Pauline P. Narvas)]

Appreciate the feedback! Let me get this shared with our v0 team.

[rahulgautama97-2599 (Vani)]

Prompting it to use gpt-5 exclusively doesnt’ work too.

”use gpt-5 model for this task. Do not use any other models”

But it still uses the md model.

By when do you think the team could roll out model selection in place of the AGENT placeholder again? I’ll decide to either wait for try something else in the meantime depending on the timelines.