Wirestack
OpenAI releases GPT Image 2.6 Sunburst and Flare with complexity control, SVG and animated GIF output (November 4, 2026)
GPT Image 2.6 Sunburst and Flare add a complexity setting, markup-guided edits, SVG output and animated GIFs on the Image API.
Your keys
0 of 1 ready
Create each key on its own page, paste it below, then copy the finished lines into your project's .env file. What you paste stays in this tab. It is never sent to Wirestack or saved.
- OpenAI API keyOPENAI_API_KEYGet key
Click Create new secret key
What you get
On November 4, 2026 OpenAI released GPT Image 2.6 as two models for image generation and editing:
gpt-image-2.6-sunburstfor detailed visual work.gpt-image-2.6-flarefor fast iteration.
Both work on v1/images/generations and v1/images/edits only. Both add four things through the Image API:
- Complexity control. The
complexityfield sets how much the model plans before it draws. Values arelow,mediumandhigh. If you leave it out, both models usehigh. Lower suits small edits, like a new background. Higher helps with dense text and busy layouts, but can be slower and change more than you asked. Changing complexity has no separate fee. - Markup-guided edits. Send a transparent PNG with circles or sketches as
markup, and say what to change inprompt. This also works on GPT Image 2.5 models. - SVG output. Set
output_format: "svg"on generations, withnset to1. You get editable vector paths, good for icons and logos. - Animated GIF output. Set
output_format: "gif"on generations or edits.frame_counttakes 2 to 16 frames (default 9).frame_duration_mstakes 20 to 2000 ms per frame, rounded to 10 ms (default 200).
Prices on both model pages are the same, per 1M tokens: text input $5, cached text input $1.25, image input $8, cached image input $2, image output $30.
Older image models stop working on December 1, 2026: gpt-image-1-mini, gpt-image-1.5 (and gpt-image-1.5-2025-12-16) and chatgpt-image-latest. OpenAI names gpt-image-2.6-sunburst or gpt-image-2.6-flare as the replacement.