OpenAI introduced Images 2.6 on November 4, 2026, for creating and editing images in ChatGPT, Codex and the API. The update can create animated GIFs and generates images 50% faster than before, according to the company.
Animating characters and product images
Users can turn a mascot, character or product image into a repeating animation. OpenAI says a simple sketch can also serve as the starting point for an animated character.
Startup Town used Images 2.6 through the API to explore how animated characters could be used in everyday workplace communication.
According to OpenAI, the model is also better at preserving the appearance of characters and products, along with brand details, through successive rounds of edits.
Two variants for developers
The API offers GPT‑Image‑2.6 Flare and GPT‑Image‑2.6 Sunburst. OpenAI says Flare can generate an image in as little as six seconds at the low quality setting and improves the layout of posters and product images.
Sunburst is intended for work requiring more detail and precision, according to the company. At medium or high quality settings, OpenAI says it produces higher-quality images and maintains greater consistency across edits.
Targeted edits and SVG export
Image markup is coming to the API, allowing users to indicate where specific changes should be made. The feature is already available in ChatGPT. The API also adds SVG export for using designs on websites, in apps and in print.
A new complexity parameter lets developers set how much planning the model devotes to fulfilling a request. A separate image-quality setting controls visual detail and fidelity.
OpenAI recommends low complexity for most edits to improve speed, and medium or high complexity for scenes with many elements or constraints.
Availability in ChatGPT and Codex
Images 2.6 is available globally in ChatGPT and Codex across all subscription tiers. It can be used on desktop, mobile and the web.
