ChatGPT Images 2.6 lets people using ChatGPT and Codex generate an animated GIF from a text prompt or an uploaded image, then adjust playback speed and edit single frames. Saved reference images of a person, pet, or character stay available for later prompts, so the same subject does not have to be uploaded again. OpenAI released the update on November 4, 2026, as weekly image creation across ChatGPT, Codex, and the API reached 4 billion. Marketers and creators can animate a brand mascot for a campaign, turn a product shot into a loop, create reactions and memes, or use an animated storyboard to explore character movement before video production. Developers can choose GPT-Image-2.6 Flare or GPT-Image-2.6 Sunburst in the API. OpenAI says Images 2.6 generates images 50% faster than the previous version. At low quality, Flare can return an image in as little as six seconds and improves layout quality for posters and product imagery. Sunburst handles higher detail and keeps characters, products, and brand details more consistent from one edit to the next when quality is set to medium or high. The API update also adds image markup, which lets a team mark the exact area to change, and SVG export for websites, apps, and print. The ChatGPT and Codex experience is available globally on every subscription tier across web, desktop, and mobile, and both API models are available now.