Images 2.6 reaches ChatGPT, Codex, and the API
On 4 November 2026 OpenAI published Images 2.6. The page says generation is 50% faster, with GIFs and two API models, Flare and Sunburst. Price was not read.
OpenAI published Images 2.6 on 4 November 2026, in ChatGPT, Codex, and the API. The page says generation is 50% faster than before.
The API has two models. GPT-Image-2.6 Flare, with quality set to low, can generate an image in as little as six seconds. The page also says Flare improves layout quality for posters, product imagery, and other professional visuals. GPT-Image-2.6 Sunburst, at medium or high quality, is the option for more detail and more consistency across edits.
The page describes GIFs, to put motion in an image, and image markup in the API, to mark the point of an edit. SVG export is in the same announcement. A complexity parameter adjusts how much planning the model does. The page recommends low complexity for most edits.
OpenAI writes that people create 4 billion images a week across ChatGPT, Codex, and the API, more than half a billion a day on average. That is a sentence on the page, not a count by this desk.
Images 2.6 is available globally in ChatGPT and Codex, on all subscription tiers, on desktop, mobile, and web. Flare and Sunburst are in the API. The page points to a pricing table and a system card. Neither was opened. There is no price in this note.
The @OpenAI thread that day confirms GIFs, a saved reference image for reuse, and the two API models. When this desk read the main post, X showed 3.6 million views.