OpenAI Images 2.6 adds faster generation, GIFs, and editing controls

OpenAI announced Images 2.6 on November 4 for ChatGPT, Codex, and the API. Developers can use GPT-Image-2.6 Sunburst or GPT-Image-2.6 Flare for image generation and editing. The release also adds animated GIF output, SVG generation, markup-guided editing, and a complexity control. (https://openai.com/index/introducing-images-2-6; https://developers.openai.com/api/docs/changelog.md)

Two models for different image tasks

The API exposes the models as gpt-image-2.6-sunburst and gpt-image-2.6-flare. OpenAI positions Flare for faster generation and says it can produce an image in as little as six seconds when quality is set to low. Sunburst is positioned for higher-quality output and greater consistency across edits at medium or high quality settings. OpenAI says Images 2.6 generates images 50% faster than its previous generation; that is the company’s stated comparison, not a latency guarantee for an individual request. (https://openai.com/index/introducing-images-2-6; https://developers.openai.com/api/docs/models/gpt-image-2.6-sunburst; https://developers.openai.com/api/docs/models/gpt-image-2.6-flare)

New output and editing controls

Images 2.6 supports animated GIF creation and SVG exports. Markup-guided editing, previously available in ChatGPT, is now available through the API for supported GPT Image 2.5 and 2.6 models. A new complexity parameter lets developers adjust how much planning the model applies to a request, separately from the image-quality setting that controls visual detail and fidelity. (https://openai.com/index/introducing-images-2-6; https://developers.openai.com/api/docs/guides/image-generation#gpt-image-26)

The two controls address different choices: quality selects the requested visual fidelity, while complexity changes how much planning the model applies. Consult the current image-generation guide and test both settings against representative images before changing a production workflow.

Availability

OpenAI says Images 2.6 is available globally in ChatGPT and Codex across subscription tiers on desktop, mobile, and web. The two named models are available through the API; the launch page does not specify API eligibility requirements or prices. (https://openai.com/index/introducing-images-2-6)

Sources

• OpenAI — “Introducing Images 2.6” (November 4, 2026): https://openai.com/index/introducing-images-2-6
• OpenAI Developers — API changelog: https://developers.openai.com/api/docs/changelog.md
• OpenAI Developers — GPT-Image-2.6 Sunburst: https://developers.openai.com/api/docs/models/gpt-image-2.6-sunburst
• OpenAI Developers — GPT-Image-2.6 Flare: https://developers.openai.com/api/docs/models/gpt-image-2.6-flare
• OpenAI Developers — Image generation guide: https://developers.openai.com/api/docs/guides/image-generation#gpt-image-26