What happened

On 4 November 2026 OpenAI introduced Images 2.6, launching it in ChatGPT, Codex and the API. The headline addition is animated GIFs; OpenAI also says images are generated 50% faster than before and that edits keep characters, products and brand details more consistent. We read the page in its Romanian version on openai.com.

Key details

  • Speed: OpenAI says generation is 50% faster, and that GPT-Image-2.6 Flare can produce an image in as little as six seconds at low quality.
  • API models: GPT-Image-2.6 Flare is described as the fast option, with better composition for posters and product images; GPT-Image-2.6 Sunburst offers higher-quality generation and better consistency between edits at medium or high quality.
  • GIFs: OpenAI shows GIFs made from a sprite sheet of frames, aimed at animated mascots, reactions and storyboards.
  • API controls: image annotation, already in ChatGPT, comes to the API; SVG export; and a new “complexity” setting that is separate from “quality.”
  • Usage claim: OpenAI says people create 4 billion images a week across ChatGPT, Codex and the API, about half a billion a day.
  • Availability: available now worldwide in ChatGPT and Codex on all subscription plans (desktop, mobile, web), and Flare and Sunburst are available in the API. OpenAI links a separate pricing page and a system card; we did not open either.
  • Partners quoted: OpenArt, Figma Weave and Picsart, and early-access examples from Picsart, fal, Sable and Higgsfield.

Why it matters

For people who already use ChatGPT for images, the practical change is faster results and a way to produce short looping animations without a separate tool. For developers, the Flare/Sunburst split and the complexity setting let them trade speed against quality and detail.

Caveats: the speed and usage numbers are OpenAI’s; the page gives no baseline for “50% faster,” no independent tests and no prices in its text; and it does not state limits for free-plan users.

Disclosure: Claude, made by Anthropic, was one of the AI tools used to research and draft this article. All figures are OpenAI’s unless stated otherwise.

Sources

  1. Introducing Images 2.6 Primary source , OpenAI