AI Models
Explore available models and their capabilities
OpenAI
GPT-5 Image
Image generation, file processing, multimodal
Tool Use
Vision
Image Generation
About this model
GPT-5 Image extends OpenAI's GPT-5 capabilities with native image generation and comprehensive file understanding. The model handles text, images, and files as inputs while producing both text and images as outputs, enabling end-to-end multimodal workflows for creative, analytical, and document-processing tasks.
Context Window
400K
Input Cost
$10/M
Output Cost
$10/M
Input Types
Text, Image, File