Image Edits

For Image Editing models, see the list of models with Edit label.

Curl

curl -X POST "https://api.imagerouter.io/v1/openai/images/edits" \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "prompt=YOUR_PROMPT" \
-F "model=openai/gpt-image-1" \
-F "image[]=@your_image1.webp" \
-F "image[]=@your_image2.webp" \
-F "mask[]=@your_mask.webp"

Javascript

const formData = new FormData()
formData.append('prompt', 'YOUR_PROMPT')
formData.append('model', 'openai/gpt-image-1')

// Add your image files (up to 16)
const imageFile1 = await fetch('your_image1.webp').then(r => r.blob())
formData.append('image[]', imageFile1)
// or from local file
const imagePath = '/home/phoenics/projects/Image router/materials/logo.png'
const imageBuffer = fs.readFileSync(imagePath)
const imageBlob = new Blob([imageBuffer], { type: 'image/png' })
formData.append('image[]', imageBlob, path.basename(imagePath))

// Add mask file - some models support/require it
//const maskFile = await fetch('your_mask.webp').then(r => r.blob())
//formData.append('mask[]', maskFile)

const response = await fetch('https://api.imagerouter.io/v1/openai/images/edits', {
method: 'POST',
headers: {
  'Authorization': 'Bearer YOUR_API_KEY'
},
body: formData
})

const data = await response.json()
console.log(data)

Python

import requests

url = "https://api.imagerouter.io/v1/openai/images/edits"
headers = {
  "Authorization": "Bearer YOUR_API_KEY"
}

files = {
  "image[]": [
      open("your_image1.webp", "rb"),
      open("your_image2.webp", "rb")
  ],
  "mask[]": open("your_mask.webp", "rb")
}

payload = {
  "prompt": "YOUR_PROMPT",
  "model": "openai/gpt-image-1",
}

response = requests.post(url, files=files, data=payload, headers=headers)
print(response.json())

Post parameners:

• prompt* Text prompt for editing the image.
• model* Model to use for image editing. Select from models that has “edit” label on them.
• image[]* Image files to be edited. Different models support different quantity of input images (usually 1 to 16).
• mask[] Some models require a mask file to specify areas to edit.
• quality [auto, low, medium, high] - default “auto”; Supported models have “quality” feature label here
• response_format [url, b64_json] - default “url”.

Currently, size is not supported. Please contact me if you miss anything.