OpenAI Launches Images 2.6: ChatGPT Can Now Make GIFs
OpenAI has launched ChatGPT Images 2.6, an update to its image generation system that adds animated GIF creation, faster generation, and more precise editing controls. Announced on November 4, 2026, the release is available globally in ChatGPT and Codex across all subscription tiers on desktop, mobile, and the web, with two new models for developers in the API.
GIFs come to ChatGPT
The headline feature is native GIF creation. Users can describe an animation in words or upload a photo and ask ChatGPT to animate it, producing a short looping GIF without opening a separate animation tool. Playback speed can be adjusted, and individual frames can be edited.
OpenAI positions the feature for marketers and creators: animating a brand mascot for a campaign, creating reactions and memes for social media, or building animated storyboards to explore character movement before video production. Even a simple sketch can become an expressive animated character, according to the announcement. Town, a startup building an AI work assistant, used Images 2.6 in the API to explore how animated characters could add personality to everyday work interactions.
One caveat for readers who want to try it right away: GIF creation is still rolling out. Independent testing by Decrypt found the feature missing on its test accounts, and TechRepublic also reports that GIF creation is still rolling out even though Images 2.6 itself is broadly available. If the option has not appeared in your account yet, it should arrive over the coming days.
Faster generation and steadier edits
OpenAI says Images 2.6 generates images 50 percent faster than before. The update also aims to fix a familiar frustration with AI image editing: change one detail and the rest of the image shifts. Images 2.6 adds saved reference images, so a character, product, or brand element can be reused across prompts while staying consistent.
For developers, the API gains two new models. GPT-Image-2.6 Flare is built for speed and can generate an image in as little as six seconds when quality is set to low. It also improves layout quality for posters, product imagery, and other professional visuals. GPT-Image-2.6 Sunburst is built for greater detail and consistency across edits when quality is set to medium or high.
The API also adds image markup, previously available only in ChatGPT, so developers can pinpoint exactly where a change should be made. SVG exports make designs ready to use across websites, apps, and print. A new complexity parameter adjusts how much planning the model does for a request, with lower settings suited to quick edits and higher settings for scenes with many elements or constraints.
Both API models are priced at 8 dollars per million image-input tokens and 30 dollars per million image-output tokens, with text billed separately, according to OpenAI’s pricing page as reported by TechRepublic. The company also published a system card describing its safety evaluations and safeguards for Images 2.6.
The scale behind the release
OpenAI says people now create 4 billion images per week across ChatGPT, Codex, and the API, or more than half a billion images per day on average. Independent coverage notes that the weekly figure was about 3 billion in September, when Images 2.5 was released on September 8, 2026.
That volume helps explain the direction of the update. Image generation has become one of ChatGPT’s most used features, and the competition is no longer just about producing a single striking picture. It is about iterating quickly, keeping a character or product consistent across many images, and handing off finished assets to other tools.
Why it matters
Images 2.6 turns ChatGPT’s image tool into a small production studio. A marketer can draft a looping product animation, a designer can keep a mascot consistent across a campaign, and a developer can generate and refine assets through the API with finer control over speed, quality, and layout.
The GIF feature is the most visible change, but the editing controls may matter more over time. Reference images and markup-guided edits address the consistency problem that has made AI-generated visuals hard to use in professional work, where a brand character or product must look the same in every image. If those controls work as described, Images 2.6 moves AI image generation a step closer to being a reliable tool for everyday creative work rather than a novelty for one-off pictures.
