OpenAI has released Images 2.6 across ChatGPT, Codex, and its API, adding native animated GIF creation and cutting image generation time by 50%1,2,5.
ChatGPT users can now generate GIFs from a text prompt or an uploaded photo in a single step — a capability the chatbot previously lacked3. Once a GIF is produced, users can adjust playback speed, inspect and edit individual frames, and share the result4. OpenAI demonstrated the workflow with the prompt "can you make a gif of a cat dancing?". The company describes use cases including animating brand mascots, turning product shots into loops, and building storyboard sequences.
The GIF pipeline works by generating six sequential animation frames arranged in a three-column, two-row sprite sheet to produce seamless loops7. The rollout is gradual; at least one outlet reported the feature was not yet available on its accounts at the time of testing6.
For developers, OpenAI is shipping two new API variants: GPT-Image-2.6 Flare, optimized for speed and professional layouts, and GPT-Image-2.6 Sunburst, targeting higher-quality output with greater consistency across successive edits. With quality set to low, GPT-Image-2.6 Flare can produce an image in as little as six seconds. A newly introduced complexity parameter lets developers balance planning and execution time.
The split between a speed-oriented and a quality-oriented API model follows the structure OpenAI introduced with Images 2.5 in September.
OpenAI says users now generate more than 4 billion images per week across ChatGPT, Codex, and the API, up from 3 billion per week reported in September. On a daily basis, that exceeds half a billion images. The figures are OpenAI's own and cover all image use, not only GIFs.
Images 2.6 is available to all ChatGPT and Codex users across web, desktop, and mobile apps on every subscription tier. The release arrives months after OpenAI shut down Sora, its AI video app, in March. OpenAI began testing ads inside image generation in the US last month.