ChatGPT adds GIF generation and Images 2.6 model

On November 5, 2026, OpenAI introduced the Images 2.6 image model and, alongside it, brought GIF generation to ChatGPT. According to The Verge, users can create a GIF from a text prompt or a photo they upload, then adjust the animation speed, edit individual frames, and share the result; the report notes that ChatGPT could not natively generate GIFs before this change. Reports from The Next Web and cnBeta confirm that OpenAI added animated GIF creation to ChatGPT on top of Images 2.6, with users able to make a GIF from text or a photo and edit its frames. The Decoder adds that the update is rolling out to ChatGPT and Codex users on web, desktop, and mobile, and that the model's image consistency is strong enough to keep characters recognizable across frames, which makes flipbook-style animation possible. On the developer side, The Next Web reports that developers get two new API models, and The Decoder names them as the GPT-Image-2.6 Flare and Sunburst models. The coverage differs on scope: The Next Web only says the capability is being rolled out alongside Images 2.6, while The Decoder describes it as going to all ChatGPT and Codex users. As for volume, The Verge says OpenAI now reports that ChatGPT and the API generate more than 4 billion images per week, up from the 3 billion figure disclosed in September; The Next Web and The Decoder repeat only the 4 billion per week number. The current status is that the feature is being rolled out as part of Images 2.6.