Edit Image

Creates an edited or extended image given an original image and a prompt. Requires multipart/form-data content type.

This endpoint follows the OpenAI multipart image-editing contract and requires an edit-capable OpenAI image model. Other image families on AnyPath are available through POST /v1/images/generations; use GET /v1/models to see what your API key can use.

Request Body

Parameter image

Type: file

Location: body

Required: yes

The image to edit. Format, size, and dimension requirements depend on the selected model.

Parameter prompt

Type: string

Location: body

Required: yes

A text description of the desired edit.

Parameter mask

Type: file

Location: body

An additional image whose fully transparent areas indicate where the image should be edited, for models that accept a mask.

Parameter model

Type: string

Location: body

The model to use for the edit. Use an edit-capable OpenAI image model such as gpt-image-1.5; view the current list with GET /v1/models.

Parameter n

Type: integer

Location: body

The number of images to generate. Must be between 1 and 10.

Parameter size

Type: string

Location: body

The size of the generated images. Supported values depend on the selected model (for example 1024x1024).

Parameter response_format

Type: string

Location: body

The format in which the generated images are returned. Must be url or b64_json.

Parameter user

Type: string

Location: body

A unique identifier representing your end-user for abuse monitoring.

Response

Response Field created

Type: integer

Unix timestamp of when the images were created.

Response Field data

Type: array

Array of generated images.

Each object contains:

• url (string): URL of the edited image (if response_format is url)
• b64_json (string): Base64-encoded image (if response_format is b64_json)

Request Example

curl -X POST "https://api.anypath.dev/v1/images/edits" \
  -H "Authorization: Bearer sk-your-api-key" \
  -F "model=gpt-image-1.5" \
  -F "image=@sunlit_lounge.png" \
  -F "mask=@mask.png" \
  -F "prompt=A sunlit indoor lounge area with a pool" \
  -F "n=1" \
  -F "size=1024x1024"

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://api.anypath.dev/v1"
)

response = client.images.edit(
    model="gpt-image-1.5",
    image=open("sunlit_lounge.png", "rb"),
    mask=open("mask.png", "rb"),
    prompt="A sunlit indoor lounge area with a pool",
    n=1,
    size="1024x1024"
)

print(response.data[0].url)

import OpenAI from 'openai';
import fs from 'fs';

const client = new OpenAI({
  apiKey: 'sk-your-api-key',
  baseURL: 'https://api.anypath.dev/v1'
});

const response = await client.images.edit({
  model: 'gpt-image-1.5',
  image: fs.createReadStream('sunlit_lounge.png'),
  mask: fs.createReadStream('mask.png'),
  prompt: 'A sunlit indoor lounge area with a pool',
  n: 1,
  size: '1024x1024'
});

console.log(response.data[0].url);

package main

import (
    "bytes"
    "fmt"
    "io"
    "mime/multipart"
    "net/http"
    "os"
)

func main() {
    body := &bytes.Buffer{}
    writer := multipart.NewWriter(body)

    image, _ := os.Open("sunlit_lounge.png")
    defer image.Close()
    part, _ := writer.CreateFormFile("image", "sunlit_lounge.png")
    io.Copy(part, image)

    mask, _ := os.Open("mask.png")
    defer mask.Close()
    maskPart, _ := writer.CreateFormFile("mask", "mask.png")
    io.Copy(maskPart, mask)

    writer.WriteField("prompt", "A sunlit indoor lounge area with a pool")
    writer.WriteField("n", "1")
    writer.WriteField("size", "1024x1024")
    writer.Close()

    req, _ := http.NewRequest("POST", "https://api.anypath.dev/v1/images/edits", body)
    req.Header.Set("Authorization", "Bearer sk-your-api-key")
    req.Header.Set("Content-Type", writer.FormDataContentType())

    client := &http.Client{}
    resp, _ := client.Do(req)
    defer resp.Body.Close()

    result, _ := io.ReadAll(resp.Body)
    fmt.Println(string(result))
}

<?php
$ch = curl_init('https://api.anypath.dev/v1/images/edits');

$image = new CURLFile('sunlit_lounge.png', 'image/png', 'sunlit_lounge.png');
$mask = new CURLFile('mask.png', 'image/png', 'mask.png');

curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => [
        'Authorization: Bearer sk-your-api-key'
    ],
    CURLOPT_POSTFIELDS => [
        'image' => $image,
        'mask' => $mask,
        'prompt' => 'A sunlit indoor lounge area with a pool',
        'n' => 1,
        'size' => '1024x1024'
    ]
]);

$response = curl_exec($ch);
curl_close($ch);

$data = json_decode($response, true);
echo $data['data'][0]['url'];

Response Example

{
  "created": 1706000000,
  "data": [
    {
      "url": "https://..."
    }
  ]
}

Notes

Image edits require an edit-capable OpenAI image model such as gpt-image-1.5. Depending on the model, the source image uses transparent areas to mark where the edit applies, or you provide a separate mask image.