OpenAI adds GIF creation and reference images to ChatGPT and Codex
Images 2.6 generates about 50% faster, while the API gets separate Flare and Sunburst models for speed and quality.

OpenAI has released Images 2.6 across ChatGPT, Codex and its API, adding GIF creation, reference-image workflows and more precise editing. The company says the system generates images about 50% faster than its previous version.
People can create a GIF from a prompt or an existing photo, then adjust its speed and frames. OpenAI is positioning the feature for reactions, brand mascots, product loops and animated storyboards. Reference images are meant to keep characters, products and brand details consistent through repeated edits.
For developers, the API now offers two models. GPT-Image-2.6 Flare prioritizes speed and can produce a low-quality image in as little as six seconds. GPT-Image-2.6 Sunburst targets higher fidelity and stronger consistency across edits at medium or high quality. The API also gains markup-based edits, SVG export and a complexity control that changes how much planning the model applies to a scene.
Images 2.6 is available globally in ChatGPT and Codex on all subscription tiers across web, desktop and mobile. Flare and Sunburst are available through the API. OpenAI says users now generate about four billion images per week across ChatGPT, Codex and the API.



