Image Editing API

The image editing interface modifies the original image according to the prompt (such as changing the background, altering elements, stylizing, etc.). Both GPT-Image and the Gemini image series can be used.

Interface

POST https://api.4allapi.com/v1/images/edits

multipart/form-data format, main fields:

Field	Description
model	Image model name, such as gpt-image-2, gemini-3.1-flash-image
image	Original image file (multiple allowed, image[])
prompt	Editing instruction

Examples

curl https://api.4allapi.com/v1/images/edits \
  -H "Authorization: Bearer $AIPROXY_KEY" \
  -F model="gpt-image-2" \
  -F image="@product.png" \
  -F prompt="Replace the background with a cozy Christmas living room scene, keeping the product subject unchanged"

resp = client.images.edit(
    model="gpt-image-2",
    image=open("product.png", "rb"),
    prompt="Replace the background with a seaside sunset scene",
)
print(resp.data[0].url or resp.data[0].b64_json[:50])

Key Usage Notes

• For multiple inputs (such as a product image + a reference style image), pass multiple image fields in order, and specify each image’s role in the prompt;
• Editing is charged per request as well, and the aspect ratio/resolution are still controlled by the model name suffix;
• To keep person/product consistency, explicitly state “keep the subject unchanged” in the prompt, and prefer an output tier with a resolution close to the original image;
• Timeout and retry strategies are the same as Image Call Best Practices.