AI Models
Explore available models and their capabilities
OpenAI
GPT-5.4 Image 2
Multimodal image generation, reasoning, coding in one model
Tool Use
Vision
Image Generation
About this model
GPT-5.4 Image 2 extends GPT-5.4 with native image generation alongside text output, enabling rich multimodal workflows that move seamlessly between reasoning, coding, and visual generation within the same interaction. It accepts text and image inputs and produces both text and images, making it well suited for design exploration, illustrated explanations, and integrated creative pipelines.
Context Window
272K
Input Cost
$8/M
Output Cost
$15/M
Input Types
Text, Image