Edit Image

Edit or extend an existing image from a text prompt using image editing models. Accepts multipart/form-data (for file uploads) or application/json (with image references as base64 data URLs or file IDs).

POST /v1/images/edits

Edit image

cURL

curl --request POST \
  --url https://router.requesty.ai/v1/images/edits \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form model=azure/openai/gpt-image-1 \
  --form 'prompt=<string>' \
  --form 'image[]=<string>' \
  --form mask='@example-file' \
  --form image[].items='@example-file'

200

{
  "created": 1719000000,
  "data": [
    {
      "url": "<string>",
      "b64_json": "<string>"
    }
  ]
}

Edit or extend an existing image from a text prompt using OpenAI compatible image editing models through Requesty’s routing.

Base URL

https://router.requesty.ai/v1/images/edits

Authentication

Include your Requesty API key in the request headers:

Authorization: Bearer YOUR_REQUESTY_API_KEY

Example Request

The endpoint accepts both multipart/form-data (the OpenAI SDK default for file uploads) and application/json (with image references as base64 data URLs or file IDs).

multipart/form-data

curl https://router.requesty.ai/v1/images/edits \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  -F "model=azure/openai/gpt-image-1" \
  -F "prompt=Make the sky a dramatic sunset" \
  -F "image[]=@./photo.png" \
  -F "size=1024x1024" \
  -F "quality=auto"

application/json

curl https://router.requesty.ai/v1/images/edits \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  -d '{
    "model": "azure/openai/gpt-image-1",
    "prompt": "Make the sky a dramatic sunset",
    "images": [
      { "image_url": "data:image/png;base64,iVBORw0KGgo..." }
    ],
    "size": "1024x1024",
    "quality": "auto"
  }'

Supported Models

• azure/openai/gpt-image-1 OpenAI’s GPT Image 1 model via Azure
• azure/openai/gpt-image-1.5 OpenAI’s GPT Image 1.5 model via Azure

Masked Edits

Provide a mask image to restrict edits to a specific region. Transparent pixels in the mask are the area that will be regenerated.

curl https://router.requesty.ai/v1/images/edits \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  -F "model=azure/openai/gpt-image-1" \
  -F "prompt=Replace the background with a forest" \
  -F "image[]=@./portrait.png" \
  -F "mask=@./mask.png" \
  -F "size=1024x1024"

Transparent Backgrounds

Use the background parameter together with output_format=png (or webp) to produce edits with transparent backgrounds:

curl https://router.requesty.ai/v1/images/edits \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  -F "model=azure/openai/gpt-image-1" \
  -F "prompt=Isolate the product on a transparent background" \
  -F "image[]=@./product.png" \
  -F "background=transparent" \
  -F "output_format=png"

Error Handling

The API returns standard HTTP status codes:

• 200 Success
• 400 Bad Request (invalid parameters)
• 401 Unauthorized (invalid API key)
• 413 Payload Too Large (uploaded images exceed the size limit)
• 429 Rate Limited
• 500 Internal Server Error

This endpoint is fully compatible with the OpenAI Images API. You can use the OpenAI SDK’s client.images.edit() method directly.

To generate a new image from scratch rather than edit an existing one, use the Create Image endpoint. See the Image Generation feature guide for a full comparison.

Authorizations

Authorization · string · header · required

API key for authentication

Body

multipart/form-dataapplication/json

model · string · required

The model to use for image editing

Example:

"azure/openai/gpt-image-1"

prompt · string · required

A text description of the desired edit

image[] · file[] · required

One or more image files to edit. Repeat the image[] field to upload multiple images (up to 16 for GPT image models).

size · enum<string>

Output size. Defaults to auto.

Available options: auto, 1024x1024, 1536x1024, 1024x1536

quality · enum<string>

Image quality. Defaults to auto.

Available options: auto, high, medium, low

mask · file

Optional mask image file. Transparent pixels mark the area that will be regenerated.

Response

200

application/json

Image edit response

created · integer · required

The Unix timestamp of when the image was created

Example:

1719000000

data · object[] · required

The list of generated images

Show child attributes