How do I go back to the default models?

Steps

The page tells you to leave a tier on its default unless you need a specific model. Resetting returns you to that built-in choice.

STEPS

Good to know

Each tier has its own default. The large tier carries the label in its list. For the others, compare the dropdown with the Models used table in Documentation if you are unsure.

There is no single reset button on the tab, so you set each tier by hand. Check all three. Any tier still showing an old pick keeps using it.

A tier set to a Custom… id needs the dropdown moved off Custom before you save. Read the custom id steps to see how that option works.

This reset does not touch the credential on the same tab. Your key stays in place.

The defaults are chosen so the costly model does only the work where it changes the outcome. That is why the page tells you to leave a tier alone unless you have a need. Learn more in the explanation of model tiers.

Need help? Write to us on the contact page.

After you save, open the tab again and read all three dropdowns once more. Your last saved choice persists, so what you see is what the next scan will use, which is a calm way to finish the job. Should a tier look wrong, fix it and save again, then run a small scan on a test target to see the result for yourself.

Related questions

• How do I pick which AI model each tier uses?
• How do I use a model that isn't in the dropdown?
• What are the Deep analysis, Recon & exploitation and Lightweight tasks tiers?
• How do I check that my AI provider credential works?
• Should I use an API key or a subscription OAuth token for my AI provider?

Full tutorial

AI provider settings: included allowance, your own credential and models

Step-by-step, with annotated screenshots.

Updated 8 October 2026 · Back to the help centre