How can I integrate the GPT Image 2.6 API into my website?

Call the images endpoint with GPT-Image-2.6 Flare or GPT-Image-2.6 Sunburst. Keep the key on your server.

This page does that through KIE when a KIE API key is set. The browser sends the prompt to this site. The site creates the task. The key never has to live in the page.

The request this page sends

The site asks KIE to create a task, then waits for the image. A still image looks like this:

{ "model": "gpt-image-2-6/economy-text-to-image", "input": { "prompt": "A clear serum bottle in a splash of blue water.", "aspect_ratio": "1:1", "resolution": "1K", "background": "auto", "output_format": "png" } }

Square, wide, and portrait become 1:1, 3:2, and 2:3. The poster shape becomes 3:4. This call stays at 1K. KIE returns a still image, so the GIF and SVG tabs do not produce those files through this call.

Edits

A marked edit is a separate call from a fresh prompt. The mark is a transparent PNG the same size as the first image, and it cannot be combined with a mask. Up to four images can go along. GIF and SVG are generation-only, so leave them out of that call.

If the key is missing, this page says so and does not invent a picture. Official details of the model are in Introducing Images 2.6.