GPT Image 2.5

Use one exact model ID for every request:

• gpt-image-2.5-flare — faster generation.
• gpt-image-2.5-sunburst — higher-fidelity output and editing control.
• gpt-image-2.5-flare:official — Flare using the official, token-billed variant.
• gpt-image-2.5-sunburst:official — Sunburst using the official, token-billed variant.

Do not send gpt-image-2.5 or gpt-image-2.5:reverse; they are not model IDs.

Setup: See authentication for token setup.

Generate

curl -X POST https://api.acedata.cloud/openai/images/generations \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-image-2.5-flare","prompt":"A clean product photograph on a pale studio background, no text","size":"1024x1024","n":1}'

Edit

curl -X POST https://api.acedata.cloud/openai/images/edits \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -F "model=gpt-image-2.5-sunburst" \
  -F "prompt=Keep the subject and composition; change only the background to dark navy." \
  -F "image=@input.png" \
  -F "size=1024x1024" \
  -F "n=1"

The result is in data[].url.

Shared contract

• size may be auto or WIDTHxHEIGHT.
• Custom dimensions use multiples of 16, max side 3840, 655,360–8,294,400 pixels, and aspect ratio at most 3:1.
• quality accepts auto, low, medium, or high.
• n accepts 1–10 and billing uses the number of images returned. Use URL output for n>1; b64_json requires n=1.
• The :official variants bill for actual text, reference-image, and output-image tokens; use returned usage records for final cost.
• For long jobs, pass async: true or callback_url, then poll POST /openai/tasks with {"id":"<task_id>"}.
• Image editing accepts URL input in JSON or local files with multipart form data.