
OFFICIAL Written by GPN · Nov 5, 2026, 10:02 AM ET · OpenAI Images 2.6 · Tech
OpenAI has launched Images 2.6, the next version of its image generation, now live in ChatGPT, Codex and the API — and the headline feature is motion: you can now turn still images into looping GIFs.
The update generates images 50% faster than before, and the new GIF tools let marketers animate a mascot, creators turn a product shot into an eye-catching loop, or storytellers sketch out animated storyboards before video production. Character, product and brand details are meant to stay consistent as you refine an image, so edits keep the look you started with. OpenAI says people now create 4 billion images per week across ChatGPT, Codex and the API — more than half a billion a day.
For developers, the API offers two flavours of the new model: GPT-Image-2.6 Flare, which can generate an image in as little as six seconds at low quality and improves layout for posters and product imagery, and GPT-Image-2.6 Sunburst, aimed at higher-quality generation with greater consistency across edits at medium or high quality. Image markup, already available in ChatGPT, comes to the API so teams can point to exactly where a change should happen, alongside SVG exports and a new complexity setting that controls how much planning the model does for a request. Images 2.6 is available globally today in ChatGPT and Codex across all subscription tiers on desktop, mobile and web.