OpenAI releases Images 2.6 with GIFs and two API models

OpenAI has released Images 2.6 in ChatGPT, Codex, and the API, adding GIF output and saying it generates images 50% faster than before.

OpenAI adds motion and faster generation. OpenAI published "Introducing Images 2.6" on November 4, 2026. The company says users can add motion with GIFs, from an animated brand mascot or character to a looping product shot, and can keep characters, products, and brand details consistent while editing.

The post does not name the earlier version behind the 50% speed comparison. OpenAI also says people now create 4 billion images a week across ChatGPT, Codex, and the API, more than half a billion a day on average.

Two new API models split speed and detail. In the API, OpenAI is offering GPT-Image-2.6 Flare (gpt-image-2.6-flare) and GPT-Image-2.6 Sunburst (gpt-image-2.6-sunburst). OpenAI says that with quality set to low, Flare can generate images in as little as six seconds, and that it improves layout quality for posters, product imagery, and other professional visuals.

Sunburst is for work that needs greater detail, with higher-quality generation and greater consistency across edits when quality is set to medium or high. Both models accept text and image inputs and return images.

GIF output has set limits in the Image API. The image generation guide says both models support complexity control, markup-guided edits, SVG output, and animated GIF output. GIF output is set on the generations endpoint; the image edit endpoint does not support it.

Developers can set a frame count from 2 to 64, defaulting to 9, and a frame duration from 20 to 2,000 milliseconds, rounded to 10 milliseconds, defaulting to 200.

Markup, SVG export, and a new complexity control come to the API. Image markup, already in ChatGPT, comes to the API, and SVG export can be used on websites, in apps, and in print. The guide documents markup-guided edits for GPT Image 2.5 and 2.6.

A complexity setting controls how much planning the model does. OpenAI recommends low for most edits, and medium or high for scenes with many elements or constraints. If omitted, both 2.6 models use high, and changing it carries no separate fee. Quality stays a separate control, with low, medium, high, xhigh, and max listed for the 2.6 models.

Pricing matches the 2.5 image models. OpenAI says Images 2.6 is available globally today in ChatGPT and Codex on all subscription tiers, on desktop, mobile, and web, and both API models are available. The pricing page lists Flare and Sunburst at $5 per million text input tokens ($1.25 cached), $8 per million image input tokens ($2 cached), and $30 per million image output tokens.