OpenAI releases GPT-Image-2.6 Flare and Sunburst image models in ChatGPT and API

AIfal says GPT Image 2.6 is now available on its platform. The model adds markup editing, which lets users draw circles, arrows and notes on an image to guide edits, and animated GIF output for both text-to-image and edit. It also offers five reasoning effort levels, from low to max.

AIOpenAI has released the GPT-Image-2.6 Flare and Sunburst image models in ChatGPT and through APIs. According to the post, Images 2.6 adds GIF generation and reference images, and generates images 50% faster than before. It is available globally today in ChatGPT and Codex across all subscription tiers on desktop, mobile, and web, with image-to-image and text-to-image pricing of $8/$5 input and $30 output.

AIOpenAI introduces two new image models for developers, GPT-Image-2.6 Flare and Sunburst. Flare generates images in as little as six seconds, while Sunburst offers higher-quality generation and greater consistency across edits. Image markup and SVG exports give developers more ways to refine and use generated images.

AIOpenAI says it is bringing GPT-Image-2.6 to Codex and the API through two new image models, Flare and Sunburst. The company says both generate images 50% faster than before. It also says Sunburst keeps details more consistent across edits at medium or high quality.