Faster Image Generation
OpenAI has launched Images 2.6 on November 4, 2026, introducing significant updates that enhance image generation speed and expand editing capabilities. The new version produces images 50% faster than its predecessors, allowing users to create approximately 4 billion images weekly across ChatGPT, Codex, and the API, averaging over half a billion images daily.
Model Variants and Performance
The API now features two model variants: GPT‑Image‑2.6 Flare and GPT‑Image‑2.6 Sunburst. Flare can generate images in as little as six seconds at low quality, while Sunburst is designed for higher-quality outputs and improved consistency across edits when set to medium or high quality. Additionally, Flare enhances layout quality for professional visuals, such as posters and product imagery.
GIF Creation Capabilities
Images 2.6 introduces native GIF creation, enabling users to produce animated sprite sheets and seamless looping sequences from a single prompt. This feature allows for a variety of animated content, from character loops to reaction GIFs, and even simple sketches can be transformed into animated characters. Coco Mao, CEO & Co-founder at OpenArt, emphasized that “GIFs are the native language of social media, and GPT‑Image‑2.6 lets every OpenArt creator speak it fluently from a single prompt.”
Enhanced API Editing Controls
The API also gains new editing features, including image markup for precise edits, SVG exports for design reuse, and a complexity parameter that dictates the level of planning the model applies. OpenAI recommends using low complexity for faster edits and medium to high complexity for scenes with numerous elements or constraints. Itay Schiff, Creative Director at Figma Weave, noted that GPT‑Image‑2.6 merges speed with creative control, enhancing workflows in Figma Weave.
Availability and Pricing
Images 2.6 is available globally today in ChatGPT and Codex across all subscription tiers on desktop, mobile, and web. The GPT‑Image‑2.6 Sunburst and GPT‑Image‑2.6 Flare models are accessible via the API, with pricing details provided alongside the release.
Original source: OpenAI News