GPT Image 2 Image Edits

Overview

Use image edits when you already have a source image and want GPT Image 2 to modify style, replace elements, adjust composition, or create variations from that starting point.

Endpoint

Method: POST
URL: https://api.gptimageapi.dev/v1/images/edit

Authentication

Include your API key in the Authorization header. Don't have one yet? Create an API key here.

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Request Body

{
  "prompt": "Turn this product shot into a premium studio image with softer reflections and a pale gray seamless backdrop.",
  "image": "https://example.com/image.jpg",
  "model": "gpt-image-2",
  "size": "4:3",
  "quality": "high",
  "n": 1
}

Parameters

prompt (required): The change you want the model to make.
image (required): A source image URL or base64 data URL.
model (optional): Use gpt-image-2.
size (optional): Output aspect ratio such as 1:1, 4:3, 16:9, 9:21, 1:2, or 2:1.
quality (optional): low, medium, or high.
n (optional): Number of outputs to generate.

Credit usage is based on quality: low = 4, medium = 8, high = 16 per image.

Good edit requests usually include

What should stay unchanged.
What should be replaced, removed, or restyled.
The target aesthetic or lighting direction.
Any required text that must appear in the final image.

Response

{
  "code": 0,
  "message": "ok",
  "data": {
    "images": [
      {
        "url": "https://cdn.gptimageapi.dev/edits/1234567890.png"
      }
    ]
  }
}

Prompting notes

If part of the source image must stay fixed, say so explicitly.
Describe the target aesthetic after you describe the required structural changes.
Use one clear source image whenever possible for the first pass.
When exact text matters, keep it short and place it in quotes.

Examples

curl

curl -X POST "https://api.gptimageapi.dev/v1/images/edit" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Turn this product shot into a premium studio image with softer reflections and a pale gray seamless backdrop.",
    "image": "https://example.com/image.jpg",
    "model": "gpt-image-2",
    "size": "4:3",
    "quality": "high",
    "n": 1
  }'

Node.js

async function editImage() {
  const res = await fetch('https://api.gptimageapi.dev/v1/images/edit', {
    method: 'POST',
    headers: {
      Authorization: 'Bearer YOUR_API_KEY',
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      prompt:
        'Turn this product shot into a premium studio image with softer reflections and a pale gray seamless backdrop.',
      image: 'https://example.com/image.jpg',
      model: 'gpt-image-2',
      size: '4:3',
      quality: 'high',
      n: 1,
    }),
  });

  const result = await res.json();
  if (result.code !== 0) throw new Error(result.message);
  return result.data.images[0].url;
}

Python

import requests


def edit_image():
  url = 'https://api.gptimageapi.dev/v1/images/edit'
  headers = {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
  }
  payload = {
    'prompt': 'Turn this product shot into a premium studio image with softer reflections and a pale gray seamless backdrop.',
    'image': 'https://example.com/image.jpg',
    'model': 'gpt-image-2',
    'size': '4:3',
    'quality': 'high',
    'n': 1,
  }

  res = requests.post(url, headers=headers, json=payload, timeout=60)
  res.raise_for_status()
  result = res.json()
  if result.get('code') != 0:
    raise Exception(result.get('message'))
  return result.get('data', {}).get('images', [])[0].get('url')


print(edit_image())

Next steps

Return to the quickstart for the generation endpoint.
Read the model guide for capability limits and prompting advice.

On this page