POST /v1/images/edits

Edit an existing image according to a text prompt. You can send a single base image or multiple, and optionally a mask.

• Method: POST
• Path: /v1/images/edits
• Auth: Bearer token in Authorization header
• Content-Type: multipart/form-data

Request Parameters

• model (string, required): Image editing model.
• prompt (string, required, 1..32000): Instructions for the edit.
• background (string, optional): Background control (provider-specific).
• mask (binary | null, optional): PNG mask where transparent areas will be replaced.
• n (integer ≥ 1, optional): Number of images to generate.
• quality (string, optional): Provider-specific quality preset.
• response_format (enum: url | b64_json, default url): Output format.
• size (string, optional): Resolution like 1024x1024.
• image (binary, optional): Base image file (single).
• images[] (binary[], optional): Multiple base images.

Note: Provide either image or images[].

Example Request

Python

from openai import OpenAI

client = OpenAI(base_url="https://api.naga.ac/v1", api_key="YOUR_API_KEY")

with open("image.png", "rb") as img:
    # Optional: open a mask file
    # with open("mask.png", "rb") as m:
    resp = client.images.edit(
        model="gpt-image-1",
        image=img,
        prompt="Make the sky more dramatic and add light rays",
        size="1024x1024",
        n=1,
        response_format="url",  # or "b64_json"
        # mask=m,
    )
print(resp.data)

Node.js

import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({ baseURL: "https://api.naga.ac/v1", apiKey: "YOUR_API_KEY" });

const resp = await client.images.edit({
  model: "gpt-image-1",
  image: fs.createReadStream("image.png"),
  // mask: fs.createReadStream("mask.png"), // optional
  prompt: "Make the sky more dramatic and add light rays",
  size: "1024x1024",
  n: 1,
  response_format: "url", // or "b64_json"
});
console.log(resp.data);

cURL

curl https://api.naga.ac/v1/images/edits \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F image="@image.png" \
  -F prompt="Make the sky more dramatic and add light rays" \
  -F model="gpt-image-1" \
  -F size="1024x1024" \
  -F n=1 \
  -F response_format="url"

Authentication

Provide your key as a Bearer token:

Authorization: Bearer YOUR_API_KEY

Response

Returns a JSON object with a data array of edited images. Each item contains either:

• url when response_format = "url", or
• b64_json when response_format = "b64_json".

Response Fields

• created (integer): Unix timestamp of request creation
• data (array): Array of edited image objects
  • url (string, optional): Image URL (when response_format = "url")
  • b64_json (string, optional): Base64-encoded image (when response_format = "b64_json")
  • revised_prompt (string, optional): The actual prompt used after any modifications