Magick API User Guide

Describes the integration status of `gpt-image-2` in the current project, as well as the request fields and response structure of the unified image interface.

The page path is retained to illustrate the integration status in the current project
Unified image interface: POST /v1/images/generations
Successful responses are synchronous ImageResponse

Current Integration Status

Magick API already supports the gpt-image-2 model

Public Image Interface Design

Request Routing

POST /v1/images/generations

Successful Response Structure

{
  "created": 1712345678,
  "data": [
    {
      "url": "https://example.com/generated-image.png",
      "b64_json": "",
      "revised_prompt": ""
    }
  ]
}

Standard Request Fields

The current project guarantees that the following standard fields will be properly parsed by the public image DTO:

model
prompt
n
size
quality
response_format

It is not recommended to directly rely on non-standardized fields at the top level of the public image interface.

Ready-to-Use Call Examples

The following examples apply when "the backend has already mapped gpt-image-2 as an available model":

cURL

curl --request POST \
  --url https://api.magickapi.com/v1/images/generations \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-image-2",
    "prompt": "一只橘猫坐在窗台上看夕阳，水彩画风格",
    "n": 1,
    "size": "1024x1024",
    "response_format": "url"
  }'

Python

import requests

url = "https://api.magickapi.com/v1/images/generations"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
}
payload = {
    "model": "gpt-image-2",
    "prompt": "一只橘猫坐在窗台上看夕阳，水彩画风格",
    "n": 1,
    "size": "1024x1024",
    "response_format": "url",
}

response = requests.post(url, headers=headers, json=payload, timeout=300)
response.raise_for_status()

result = response.json()
print(result)
print("image_url:", result["data"][0]["url"])

Node.js

const url = "https://api.magickapi.com/v1/images/generations";
const payload = {
  model: "gpt-image-2",
  prompt: "一只橘猫坐在窗台上看夕阳，水彩画风格",
  n: 1,
  size: "1024x1024",
  response_format: "url",
};

const response = await fetch(url, {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify(payload),
});

if (!response.ok) {
  throw new Error(await response.text());
}

const result = await response.json();
console.log(result);
console.log("image_url:", result.data?.[0]?.url);

If you prefer to receive Base64 content directly, change response_format to b64_json and read data[0].b64_json.

Image Editing

If the channel corresponding to this model supports editing capabilities, the unified editing endpoints in the current project are:

POST /v1/images/edits
POST /v1/edits

Notes

Asynchronous image tasks are supported. Please check the generated images in [Task Log] -> [Image Generation Log].

GPT Image 2