GPT Image 2 / 2.5 Image Editing API

¶ 1. Get API Key

Open the Lingxi AI Plaza application list, access the available applications, and copy the API Key.

¶ 2. Edit Using Image URL

Original image:

curl https://api.acedata.cloud/openai/images/edits \
  -H "Authorization: Bearer your API Key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "image": "https://platform2.cdn.acedata.cloud/gpt-image/d56455e2-e7f7-4bcd-b935-475b0a1e0948_0.png",
    "prompt": "Keep the mug, tabletop, camera angle, portrait layout, and soft shadow unchanged. Change only the mug color from white to vivid orange and the pale cream background to solid dark navy blue. No text and no logo.",
    "size": "1024x1536"
  }'

Successful response:

{
  "success": true,
  "task_id": "49848451-c624-4df9-9dc2-494018daaf4c",
  "trace_id": "5ac021c2-2891-4eed-bfcf-4c6668ac1be1",
  "created": 1788831893,
  "model": "gpt-image-2",
  "data": [
    {
      "url": "https://platform2.cdn.acedata.cloud/gpt-image/49848451-c624-4df9-9dc2-494018daaf4c_0.png"
    }
  ],
  "usage": {
    "input_tokens": 775,
    "output_tokens": 1372,
    "total_tokens": 2147
  }
}

This is the editing result completed through Lingxi AI Plaza on September 8, 2026, where the mug turned orange, the background became dark navy blue, while maintaining the original composition and size of 1024×1536:

¶ 3. Upload Local Image

Using multipart/form-data:

curl https://api.acedata.cloud/openai/images/edits \
  -H "Authorization: Bearer your API Key" \
  -F "model=gpt-image-2" \
  -F "image=@input.png" \
  -F "prompt=Replace the background with a bright modern studio"

You can repeatedly pass in image, and the GPT Image series supports up to 16 reference images. The image in the JSON request can be a single URL or an array of URLs; local files are uploaded using multipart.

¶ 4. Common Parameters

Field	Description
model	gpt-image-2, gpt-image-2.5-flare (faster), gpt-image-2.5-sunburst (higher fidelity and control), gpt-image-2:official or gpt-image-2:reverse
image	JSON uses a single URL or an array of up to 16 URLs; multipart uses one or more image file fields
prompt	Editing instructions
size	auto or a compliant WIDTHxHEIGHT
n	1–10; only supports 1 when response_format=b64_json
response_format	url or b64_json
callback_url	Optional asynchronous callback address

Size rules are consistent with the generation interface: width and height must be multiples of 16, the long side must not exceed 3840, total pixels must be between 655,360 and 8,294,400, and the aspect ratio must not exceed 3:1. If size is omitted or auto is used, the model will choose the aspect ratio based on the prompt and the first reference image.

gpt-image-2, gpt-image-2.5-flare, gpt-image-2.5-sunburst, and :reverse are billed based on the number of successful images; gpt-image-2:official is settled based on the actual tokens of text input, reference image input, and image output, with the final billing based on usage records.

¶ 5. Asynchronous Callback and Troubleshooting

For long tasks, you can add:

{
  "callback_url": "https://example.com/webhooks/images"
}

An asynchronous 200 response will be {"task_id": "..."}; the final result will be called back upon completion. A synchronous request will return created and data.

Status	Check
400	Image format/quantity, parameter combinations, and size format
401	API Key and Bearer Header
429	Request frequency
504	Switch to asynchronous callback

Error responses will include a trace_id. Provide this ID when reporting issues, and do not provide the API Key.

Complete fields and real-time enumeration are subject to the OpenAI Images Edits API page. For pure text image generation, please refer to GPT Image 2 / 2.5 Image Generation.