GPT Image 2 / 2.5 Image Generation API

¶ 1. Obtain API Key

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

¶ 2. Send the First Request

curl https://api.acedata.cloud/openai/images/generations \
  -H "Authorization: Bearer your API Key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "Minimal editorial product illustration: one plain white ceramic coffee mug centered on a solid cobalt blue tabletop, pale cream background, soft shadow, clean geometric shapes, no text, no logo, portrait composition",
    "size": "1024x1536"
  }'

The successfully responded image is located at data[].url. Below is the 1024×1536 result obtained through Lingxi AI Plaza on September 8, 2026 (task d56455e2-e7f7-4bcd-b935-475b0a1e0948, trace eb938601-8192-407f-b539-1e0554b697ec):

¶ 3. Common Parameters

Field	Description
model	gpt-image-2 (default recommended), gpt-image-2.5-flare (faster), or gpt-image-2.5-sunburst (higher fidelity and control); can also explicitly choose gpt-image-2:official or gpt-image-2:reverse
prompt	Image description, up to 32,000 characters
size	auto or WIDTHxHEIGHT; width and height must be multiples of 16, with the longer side not exceeding 3840, total pixels between 655,360–8,294,400, aspect ratio not exceeding 3:1
n	1–10; only supports 1 when response_format=b64_json
quality	low, medium, high, or auto; different lines have different support and billing methods
response_format	url or b64_json
callback_url	Optional; send results to this address after long tasks are completed

Common sizes:

Ratio	1K	2K	4K
1:1	1024x1024	2048x2048	2880x2880
4:3	1536x1024	2048x1536	3264x2448
3:4	1024x1536	1536x2048	2448x3264
16:9	1792x1024	2048x1152	3840x2160
9:16	1024x1792	1152x2048	2160x3840

size: "auto" will select the aspect ratio, pixels, and layout intention based on the prompt; specify dimensions directly when precise pixels are needed.

¶ 4. Generate Multiple Images

curl https://api.acedata.cloud/openai/images/generations \
  -H "Authorization: Bearer your API Key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A small fox reading under a glowing mushroom, watercolor illustration",
    "size": "1536x1024",
    "n": 2
  }'

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 billed based on the actual tokens for text input and image output in the response. The page price is an estimate before the request, and the final amount is based on usage records.

¶ 5. Asynchronous Callback

After adding callback_url to the request body, the interface will first return {"task_id": "..."}, and upon completion, it will POST the final result to that URL; synchronous requests will still return created and data:

{
  "model": "gpt-image-2",
  "prompt": "A product poster with clear typography",
  "size": "1024x1024",
  "callback_url": "https://example.com/webhooks/images"
}

The callback receiver should use task_id for deduplication and verify the request source and data format.

¶ 6. Troubleshooting

Status	Check
400	Combination of model, prompt, size format, n, and response_format
401	Is the API Key complete? Is the Header Authorization: Bearer ...?
429	Too many requests, please try again later
504	Synchronous generation timed out; switch to callback_url

Error responses will include error.code, error.message, and trace_id. When reporting issues, provide the trace_id, do not provide the API Key.

Complete fields and real-time enumeration are based on the OpenAI Images Generations API page. For image editing, please refer to GPT Image 2 / 2.5 Image Editing.