OpenAI launches animated GIF generation in ChatGPT and Codex using the Images 2.6 model
OpenAI is expanding Images 2.6 with animated GIF generation in ChatGPT and Codex, and has released the GPT-Image-2.6 Flare and Sunburst API models featuring SVG generation and markup-guided editing. The company reports more than 4 billion images generated weekly.
Latest development: according to sources, the animated GIF generation feature in ChatGPT is gradually being rolled out not only to the web, desktop, and mobile versions of ChatGPT, but also to Codex. Users enter a text prompt or upload a photo, and the Images 2.6 model creates a flipbook-style animation, where the playback speed and individual frames can subsequently be adjusted. According to OpenAI, the model keeps a character's appearance consistent across frames better than previous models.
The same Images 2.6 release also includes two new API models for developers — GPT-Image-2.6 Flare (focused on faster generation) and GPT-Image-2.6 Sunburst (focused on higher quality), both available via the v1/images/generations and v1/images/edits API endpoints. The update also brings SVG generation, adjustable image complexity, and markup-guided editing, which is also available for supported GPT Image 2.5 models.
According to OpenAI, more than 4 billion images are now generated weekly via ChatGPT and the API, up from roughly 3 billion weekly in September. The update was released on 4 November 2026.
Why it matters
Being able to create animated GIFs directly in ChatGPT without needing an external animation tool simplifies simple graphic production for individuals and teams working with short visual content. At the same time, the new Flare and Sunburst API models give developers a choice between speed and quality in image generation, which is relevant for products that integrate image generation or image editing into their own workflows.
What was added since the original report
Verified updates
-
The rollout of GIF generation is also extending to Codex, not just ChatGPT
-
Two specific models: GPT-Image-2.6 Sunburst and GPT-Image-2.6 Flare, with technical identifiers; SVG generation is a new feature in the new models; Markup-guided editing added for GPT-Image 2.5 and 2.6 models; Adjustable complexity in image generation; Specific release date: 2026-11-04
- Two specific models: GPT-Image-2.6 Sunburst and GPT-Image-2.6 Flare, with technical identifiers
- SVG generation is a new feature in the new models
- Markup-guided editing added for GPT-Image 2.5 and 2.6 models
- Adjustable complexity in image generation
- Specific release date: 2026-11-04
Two audiences, two different impacts
What this means
For individuals
ChatGPT users can now create an animated GIF directly from a text description or an uploaded photo, and adjust the animation speed or individual frames, without needing a separate animation tool.
For a business
Companies creating marketing or social content can generate animated GIFs directly in ChatGPT without external animation tools, which may reduce the time needed for minor graphic production.
Sales and marketingCheck the original
Event sources
confirmed by 2 independent sources · 3 publishers, 2 independent. We count feeds from the same owner only once.