GPT Image 2 — Image generation API

curl https://api.quotaflow.ai/openai/v1/images/generations \
  -H "Authorization: Bearer $QUOTAFLOW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A clean editorial illustration of an AI workflow.",
    "size": "1024x1024",
    "quality": "medium",
    "response_format": "b64_json"
  }'

The active V3 profile is generation-only. Image edits, masks, multi-reference edits, async jobs, and Responses image_generation remain unavailable until each capability has its own signed audit receipt and snapshot entry. They do not fall back to legacy execution.

Request parameters

For gpt-image-2, size accepts arbitrary WIDTHxHEIGHT strings when both dimensions are divisible by 16, the aspect ratio is between 1:3 and 3:1, and the size is at most 3840x2160, with 655,360 to 8,294,400 total pixels. background=transparent requires output_format=png or webp; partial_images returns HTTP 400 because streaming is unavailable; background, moderation, and output_compression are forwarded upstream.

Not supported / differences from OpenAI

• Streaming (stream and partial_images) is unavailable; requests using it are rejected.
• OpenAI Files API references (images[].file_id and mask.file_id) are rejected because they are bound to one OpenAI account and a router cannot resolve them.
• user is accepted for compatibility but is not forwarded upstream.
• style is forwarded verbatim and the upstream decides whether it is supported.
• response_format=url is a Quotaflow extension. It returns a hosted URL with the TTL implemented by the selected output host; download it promptly because the router does not promise OpenAI's URL lifetime.
• Today, omitted quality defaults to medium; size=auto is sent upstream as 1024x1024.
• The current endpoint is synchronous only; async submission is rejected.