OpenAI releases Images 2.6 with GIF animation and two API models, Flare and Sunburst

On November 4, 2026, OpenAI released Images 2.6 in ChatGPT, Codex and the API. OpenAI says it generates images 50% faster than the previous version and keeps characters, products and brand details more consistent across edits. In ChatGPT, GIF creation is rolling out, so you can ask for a looping animation or animate a sketch, and saved reference images let you name a photo once and reuse it in later chats with an @ mention. OpenAI also says people now create 4 billion images a week across ChatGPT, Codex and the API.

In the API, developers choose between GPT-Image-2.6 Flare, which OpenAI says can return a low-quality image in as little as six seconds and handles poster and product layouts better, and GPT-Image-2.6 Sunburst for higher quality and consistency at medium or high quality. Both support markup-guided edits, SVG output, animated GIF output and a new complexity setting that controls how much planning the model does; OpenAI recommends low complexity for quick edits. Markup-guided editing also works with supported GPT Image 2.5 models.

As of November 5, 2026, both API models cost the same as GPT Image 2.5 at standard rates: $5 per million text input tokens ($1.25 cached), $8 per million image input tokens ($2 cached) and $30 per million image output tokens. Images 2.6 is available globally in ChatGPT and Codex on all subscription tiers, on desktop, mobile and web, and OpenAI published a system card for it.