AI Models
Explore available models and their capabilities
OpenAI
GPT-5.4 Image 2
Native image input + output, multimodal
Tool Use
Vision
Image Generation
About this model
GPT-5.4 Image 2 is OpenAI's multimodal model with native image generation alongside text input and output. It enables seamless visual workflows where the same model can both understand and produce images, suitable for design exploration, visual reasoning, and creative tasks.
Context Window
272K
Input Cost
$8/M
Output Cost
$15/M
Input Types
Text, Image