OpenAI has rolled out ChatGPT Images 2.6, an updated image-generation model that adds native animated GIF creation and generates images 50% faster than its predecessor. The update, announced on November 4, is available globally across ChatGPT and Codex on the web, desktop and mobile, including all subscription tiers.
The biggest addition is the ability to create animated GIFs directly from text prompts or uploaded images. Users can animate characters, create reaction images and develop simple storyboards, then change how quickly the animation plays, revise specific frames, inspect those frames individually and share the finished GIF.
OpenAI says people are now generating more than 4 billion images every week across ChatGPT, Codex and its API, up from the more than 3 billion weekly images it reported in September. Images 2.6 arrives just two months after Images 2.5, which was released on September 8, 2026.
For developers, OpenAI is adding two API models: GPT-Image-2.6 Flare, built for speed, and GPT-Image-2.6 Sunburst, built for higher-quality output. Flare can create an image in as little as six seconds on its low-quality setting, while Sunburst focuses on detail and produces sharper images that stay consistent across edits on medium or high quality.
Images 2.6 also brings support for scalable SVG export and image markup to the API, so teams can identify precise areas for changes. OpenAI said the release sharpens lighting, skin tones, materials and dense multi-column text layouts across menus, infographics, calendars and slides.
The company presented the update on X as “Images, upgraded — introducing ChatGPT Images 2.6. Now with GIFs and reference images. Plus, two new models are coming to the API with 50% faster image generation.” The GIF feature is not a full AI video tool: it focuses on short animated loops rather than longer videos.
