ChatGPT can now make animated GIFs with the new Images 2.6 model

ChatGPT can now make animated GIFs from a text prompt or an uploaded photo, according to The Verge, which reported the update on November 4. It arrives with OpenAI's new Images 2.6 model, which the company says also generates images faster.

The Verge notes that before this, ChatGPT could not natively generate GIFs in a single step. OpenAI's own announcement page was not readable when this was written, and its API changelog had no entry yet for Images 2.6, so the details below come from The Verge's report of what OpenAI said.

What ChatGPT's GIF maker does

The Verge says OpenAI's example prompt was "can you make a gif of a cat dancing?" After ChatGPT makes the GIF, you can:

• change the playback speed
• view and edit individual frames
• share the result with others

You can also start from a photo you upload instead of a text prompt.

Who gets Images 2.6

Images 2.6 is rolling out to all ChatGPT and Codex users on web, desktop and mobile, The Verge reports. Rollouts are staged, so it may not show up in your account immediately. OpenAI is also launching GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst in its API, described as faster and higher-quality options.

Those names follow OpenAI's earlier GPT Image 2.5 Sunburst and Flare models, which its API changelog lists on September 8, 2026. That entry says both use GPT Image 2 token rates and support xhigh and max quality settings. The 2.6 pricing has not been published in the sources we could read.

The usage numbers

OpenAI says users now generate more than 4 billion images a week across ChatGPT and its API, up from the 3 billion a week it reported in September.

What we don't know yet

The report doesn't say whether free users get GIF limits different from paid ones, how long a GIF can be, or what the API models cost. Check OpenAI's ChatGPT release notes and API pricing page for those details once they are posted.