AI Credits & Models

Forge uses AI credits when a request is processed by an AI model.
This includes generating UI, editing components, analyzing layouts, and running UX reviews.

Each AI-powered action consumes credits.

You can see how many credits remain in:

More menu (⋮) in the AI panel.
Forge Settings.
AI Component Creator modal in Project dashboard view.

Credit limits depend on your subscription plan.

How AI credits work

Credit usage is proportional to the amount of processing required and depends on the amount of text processed by the selected model.

Smaller updates use fewer credits, while larger UI and more complex layout generations use more credits.

For example, adjusting spacing in an existing component will usually consume fewer credits than generating a full dashboard with multiple sections.

To learn how tokens are calculated, refer to the documentation from OpenAI or Anthropic.

AI models

Forge supports models from OpenAI and Anthropic. Available models depend on your subscription plan.

Note

Model availability and versions may change over time.

Plan	Available models
Freemium	GPT Mini
Core	GPT standard models and Claude Haiku
Growth	All models
Enterprise	All models
Legacy Plans	Depends on plan configuration

If you connect your own OpenAI or Anthropic API key, available models depend on your provider account.

Which AI model should I choose

Different models are suited to different types of tasks. They also differ in how many credits they consume for similar requests.

Lightweight models (for example GPT Mini or Claude Haiku)

Good for quick edits and small UI updates such as spacing adjustments, text changes, or simple component generation.

Standard models (for example GPT standard models or Claude Sonnet)

Balanced models for most design tasks such as generating sections, combining layout and content, or refining structure.

Advanced models (for example Claude Opus)

Designed for complex reasoning and larger outputs. These models are useful for generating multi-section layouts, structured components, or detailed UX reviews.

If you are iterating on small changes, a lightweight model may be more efficient.
If you are generating larger layouts or running UX reviews, a more advanced model may produce more consistent results.