Screen Understanding: AI Model Selection Guide

Screen Understanding

Use Case Overview

This page focuses on the Screen Understanding use case, covering core requirements, recommended models, and evaluation criteria.

Selection Criteria

• Supports image/audio input

Evaluation Criteria

• Supports image/audio input

Best Practices

• Provide system prompt for context
• Monitor token usage and cost

Recommended Models

See the recommended models list for this use case (path: /en/use-cases/screen-understanding/).