Use GPT image editing models to intelligently edit and modify existing images via text descriptions. Supports multiple image formats and quality options to meet various image editing needs.
Bearer authentication format: Bearer {{API Key}}.
Request Body
The model used for image editing. Currently supports gpt-image-1, gpt-image-1.5.
Array of images to be edited (multipart/form-data). For gpt-image-1, gpt-image-1.5, each image must be in png, webp, or jpg format, under 50MB per image, with a maximum of 16 images.
Text description of the desired edited image. For gpt-image-1, gpt-image-1.5, the maximum length is 32000 characters.
Quality of the generated image, Default: auto. For gpt-image-1, gpt-image-1.5, supported values are: auto, high, medium, low.
Number of images to generate, Range: 1~10, Default: 1.
Size of the generated image, Default: auto. For gpt-image-1, gpt-image-1.5, supported values are:
1024x1024: Square
1536x1024: Landscape
1024x1536: Portrait
auto: Default
Response Parameters
Unix timestamp (in seconds) of when the image was generated.
List of generated images. Base64-encoded string of the generated image.
Only supported by gpt-image-1, gpt-image-1.5. Token usage information for image generation. Number of tokens for the input prompt (including images and text).
Detailed information about input tokens. Number of image tokens in the input prompt.
Number of text tokens in the input prompt.
Number of output tokens generated by the model.
Total number of tokens consumed for this image generation (including images and text).