OpenAI releases Images 2.6 with GIFs

OpenAI's 4 November 2026 post introduces Images 2.6 in ChatGPT, Codex, and the API. OpenAI says it generates images 50% faster than before. In the API the two models are GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst. With quality set to low, Flare can generate an image in as little as six seconds. Sunburst is the higher-detail model, and OpenAI says it holds consistency across edits better when quality is medium or high. Flare is also described as better at layout for posters and product imagery.

The post says GIFs are part of this release, for a looping animation such as a mascot or a product shot. Image markup, already in ChatGPT, comes to the API so a caller can point at the part to change. SVG export is in the API. A new complexity parameter sets how much planning the model does. OpenAI says low complexity fits a quick edit, and medium or high fits a scene with many constraints. Quality still controls visual detail. Images 2.6 is available globally in ChatGPT and Codex on all subscription tiers, on desktop, mobile, and web. The post points API prices to a separate pricing page and does not print them here.

Who it's for: someone already making pictures in ChatGPT or Codex who wants a faster edit, a GIF, or the Flare and Sunburst API models.

Fits: Best for Images stays Midjourney for a considered frame. ChatGPT stays third, for a fussy instruction or a conversation you already have. Faster generation and GIFs do not change that split. The image guide and the ChatGPT alternatives are unchanged. The verdict is unchanged.