OpenAI launches Images 2.6 in ChatGPT and Codex, supporting GIF generation from a single prompt
OpenAI has launched the Images 2.6 model in ChatGPT and Codex, with generation speed increased by 50% compared with before, and support for generating animated GIFs from a single prompt or sketch. The API offers two versions: 2.6 Flare produces an image in 6 seconds at low-quality settings, while 2.6 Sunburst is better suited to professional visual assets. OpenAI says ChatGPT, Codex and the API generate more than 4 million images per week, and all generated images carry an invisible SynthID watermark.
Why read this
AI score 66
OpenAI launches Image 2.6 in ChatGPT and Codex, detailing the speed improvements, dual API versions and GIF generation capability, to help assess changes in image generation workflows.
Topics
Body
OpenAI just made a new Image 2.6 model available in ChatGPT and Codex, and it can create images faster with more professional visuals. The new model also lets users create animated GIFs from a single prompt.
According to OpenAI, Image 2.6 can generate images 50% faster than before. Through the API, developers can choose between the faster 2.6 Flare model, which can generate images in six seconds when quality is set to low, and the 2.6 Sunburst model that’s better suited for creating professional visuals.
We have a gif for you—ChatGPT Images 2.6 is here.
ChatGPT Images 2.6 can turn your prompts and pictures into animated GIFs.
You can also keep reference images of yourself, pets, and characters ready to reuse in new creations…no need to upload them again.
Go on. Make it… pic.twitter.com/ppb9u6n3Rv
— ChatGPT (@ChatGPT) November 5, 2026
GIFs probably peaked in popularity a couple of years ago, but ChatGPT making it easy to create GIFs from a simple text prompt or a sketch may help to bring them back to the spotlight. OpenAI touted professional use cases, including creating animated brand mascots and product visuals.
OpenAI said today that more than 4 million images are now created every week across ChatGPT, Codex, and the API. All of these AI-generated images come with an invisible SynthID watermark, so they can be easily detected by tools such as Google’s new AI Content Detector or Apple’s Photos and Image Playground apps.