Skip to main content
Choose the model type per prompt - Frontier, Core or Basic - to affects the depth and speed of a response. How to decide: heavier tasks need more reasoning power; simple tasks don’t. The right model for the right task gets you a good result faster, which will help credits go further.

Model type options

Model TypeExample ModelsBest for
FrontierClaude Opus, Gemini ProComplex, multi-step workflows requiring accuracy or reasoning
Core (default)Claude SonnetMost tasks - balanced speed and reasoning
BasicClaude Haiku, Gemini FlashQuick questions, small edits, lookups

When to use each model type

A good rule of thumb: start with Core. Upgrade to Frontier if you’re getting responses that feel shallow or need lots of correction. Switch to Basic for quick questions between longer tasks.
Frontier is worth the extra credits for complex tasks:
  • Long, multi-step Agent Mode workflows
  • Output that requires precision, like UI generation
  • Tasks with many dependencies or subtle system interactions
  • Deep debugging across scenes and systems where the root isn’t clear

How to select the model type

The model selector is inline in the prompt input. Core is the default. If you want a different model type for a prompt, you need to select it before you submit the prompt.
Model Selector

Tracking credit usage

To see a breakdown of credits consumed per prompt and by model type, follow these steps:
  1. Go to: app.bezi.com/account
  2. Open the Subscriptions & Usage tab
See the Plans & Credits page for a full breakdown of how credit usage works.