OpenAI Images 2.6 Release: GIF Animation, 50% Faster Generation, and API Controls

OpenAI announced Images 2.6 on November 4, 2026, bringing faster image generation, GIF animation, and more precise editing controls to ChatGPT, Codex, and the API. The release matters because it targets both high-volume casual creation and professional visual workflows: OpenAI says people now create 4 billion images per week across those surfaces, and Images 2.6 adds motion and API-level controls on top of a 50% speed improvement.

What OpenAI announced

Images 2.6 is available globally in ChatGPT and Codex across all subscription tiers on desktop, mobile, and web, and in the API through two models: GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst. OpenAI positions the release around three changes: faster iteration, GIF animation, and more control over how images are created, edited, and carried into later stages of a project.

OpenAI also reports that people around the world now create 4 billion images per week across ChatGPT, Codex, and the API. On average, that is more than half a billion images created per day.

Faster generation and two API models

Images 2.6 generates images 50% faster than before, according to OpenAI. In the API, the two variants serve different quality and speed needs.

GPT-Image-2.6 Flare is the faster option. When quality is set to low, Flare can generate images in as little as six seconds. Flare also improves layout quality for posters, product imagery, and other professional visuals.

GPT-Image-2.6 Sunburst is aimed at work that needs greater detail and precision. It brings higher-quality image generation and even greater image consistency across edits when quality is set to medium or high.

The split lets developers choose between speed-oriented generation and higher-fidelity output within the Images 2.6 family.

GIF animation

Images 2.6 can bring motion to images with GIFs. OpenAI describes uses including animating a brand mascot or character, turning a product shot into a looping visual, creating reactions and memes for social media, and building animated storyboards to explore character movement before video production.

The feature is not limited to polished designs. OpenAI says even a simple sketch can become an expressive, animated character for videos, games, and other uses. The post illustrates the workflow with sprite-sheet prompts for seamless looping GIFs and shows a pen sketch of an owl as an example of a simple drawing that can be animated.

Town, a startup building an AI work assistant, used Images 2.6 in the API to explore how animated characters could bring more personality to everyday interactions at work, according to OpenAI.

More API control for editing and production

Images 2.6 adds several controls for developers. Image markup, which was already available in ChatGPT, comes to the API so teams can pinpoint exactly where to make specific changes. SVG exports make designs ready to use across websites, apps, and print.

A new complexity parameter lets developers adjust how much planning the model does to meet a request. Lower settings are suited to quick edits. Image quality controls visual detail and fidelity, while complexity guides how much goes into the scene.

OpenAI recommends low complexity for most editing tasks, paired with the image quality a workflow requires. For scenes with many elements or constraints, OpenAI suggests trying medium or high complexity effort.

Availability and pricing

At announcement, OpenAI said Images 2.6 is available globally today in ChatGPT and Codex across all subscription tiers on desktop, mobile, and web. GPT-Image-2.6 Sunburst and GPT-Image-2.6 Flare are available in the API. OpenAI points developers to its API pricing page for details and to the Images 2.6 system card for safety evaluations and safeguards.

Why the release matters

Images 2.6 combines three levers that matter for image generation at scale: speed, motion, and control. The 50% faster generation and six-second low-quality Flare output reduce iteration time, while GIF support extends images into short animated formats. The API additions, including image markup, SVG exports, and the complexity parameter, target teams that need to edit and productionize images rather than only generate one-off visuals.