In brief
- Images 2.6 was announced for ChatGPT, Codex and the API on 4 November 2026.
- OpenAI says the new version generates images 50% faster than the previous model.
- Developers can use the GPT-Image-2.6 Flare and Sunburst options in the API.
- The API adds editing with annotations and SVG export.
OpenAI announced Images 2.6 for ChatGPT, Codex and API users on 4 November 2026. In addition to image generation and editing, the new version adds GIF creation options. According to OpenAI, Images 2.6 generates images 50% faster than its predecessor. For the API, developers can choose between GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst to suit different needs.
What are Flare and Sunburst designed for?
OpenAI positions Flare for fast generation and iteration, and Sunburst for greater detail and visual consistency across edits. According to the company, at the low quality setting Flare can create some images in as little as six seconds. These speed and timing claims come from the provider; actual results may vary depending on the prompt and settings.
Developers can set image quality and complexity separately in the API. The quality setting affects image detail and accuracy, while the complexity setting controls how much planning the model does when preparing a response. OpenAI recommends low complexity for most editing tasks, and medium or high complexity for scenes with many elements or constraints.
GIFs, editing with annotations and SVG
Images 2.6 makes it possible to generate a GIF from a single prompt. Use cases demonstrated by OpenAI include animating characters, creating social media content and previewing character movements as a draft before video production. The company also says a sketch can be turned into an animated character.
The ability to mark an area of an image for editing was already available in ChatGPT; OpenAI is now bringing it to the API as well. This lets developers specify the area to be edited directly on an image. SVG export in the API is intended for designs used in web, app and print work. The new version also aims to preserve character, product and brand details more consistently across editing rounds.
Impact on architecture and visualization workflows
For architecture firms, interior designers and visualization teams, the announced features could be useful for tasks such as presentation graphics, animated concept narratives and targeted image edits. GIF generation offers a way to present an idea in a short animated format, while editing with annotations lets users request changes to specific parts of an image. However, the source does not explain any direct integration with architectural modeling or rendering tools.
As a result, whether these features can be used in new workflows will depend on API connectivity in existing tools and how developers implement them. SVG export also offers a file format option that may be useful in later design stages, but the source does not provide a compatibility list for architecture software. Teams using the API should test the editing process and outputs before adding the features to existing workflows, and assess usage costs based on their own API consumption. OpenAI does not specify pricing details in its announcement.
Sources
1 sourceSource texts are not republished; short quotes are marked, everything else is our own summary and commentary.
For architecture firms and visualization teams, the key promise of Images 2.6 is not a new modeling tool in itself, but faster image generation and editing. GIF and SVG options could be tested for presentations, promotional materials and concept narratives. Region-based editing may also be useful when small changes are needed to an existing image; however, the source does not explain direct compatibility with architecture software.
For teams in Turkey, the decision should center on API costs, development requirements and how well the outputs fit existing workflows. Since the speed increase is a claim made by the provider, it is best to compare quality and turnaround time using examples that resemble real projects before switching. Subscription terms and API usage costs should also be assessed separately.
Frequently asked questions
Where can OpenAI Images 2.6 be used?
OpenAI says Images 2.6 is available in ChatGPT and Codex across all subscription tiers on desktop, mobile and web. The API offers the GPT-Image-2.6 Flare and Sunburst options.
Can Images 2.6 create GIFs?
Yes. OpenAI says Images 2.6 can generate a GIF from a single prompt and turn sketches into animated characters.
Does Images 2.6 support SVG and image annotations in the API?
Yes. According to the announcement, the API supports SVG export and marking areas of an image for editing.
