OptionalbaseURL: stringProtectedapiOnly sub-classes can access the API key
Read-only getter for the OpenAI client instance
ProtectedcreateHelper method to create an error result with proper timing
ProtectedcreateHelper method to create a successful result with proper timing
Create variations of an existing image. Uses GPT-4o's multimodal capabilities to generate variations.
Edit an existing image. Note: GPT-4o Image models support image editing through the chat interface with vision. This method uses the images.edit endpoint for supported operations.
Generate image(s) from a text prompt using GPT-4o Image Generation
Get available GPT-4o Image models
Get supported methods for this provider
ProtectednormalizeHelper method to convert image input (Buffer, base64, or URL) to the format required by the specific provider. Subclasses can override as needed.
Image as Buffer, base64 string, or URL
Normalized image data
OpenAI GPT-4o Image implementation of the BaseImageGenerator class. Supports gpt-image-1.5 (December 2025) for native multimodal image generation.
This replaces the older DALL-E models with OpenAI's GPT-4o native image generation capabilities, which produce higher quality results through the ChatGPT API.