Skip to main content
Image input capabilities allow you to send images to vision-enabled AI models for analysis, description, and understanding.

Basic Image Input

Image from URL

TypeScript

Image from Local File

TypeScript

Advanced Image Analysis

Multiple Images

TypeScript

Next Steps

  1. Reasoning - Advanced reasoning capabilities
  2. CRUD Operations - Manage stored completions
Image input requires vision-capable models like GPT-4o, Claude Sonnet-4, or Gemini Pro Vision. Ensure your images are in supported formats (JPEG, PNG, WebP). Both TypeScript and Python SDKs provide comprehensive support for image analysis with proper error handling and type safety.