FreshSynapse

AI trends & daily updates, in plain English

AI Tools

ChatGPT Can Now Make GIFs: OpenAI Ships Images 2.6 With Faster Generation and Two New API Models

By FreshSynapse Editorial · · 3 min read

A man holding a professional camera in a studio, with a video camera on a tripod in front of him

Photo: Hippopx (public domain). Illustrative image.

What happened. OpenAI released Images 2.6 on 4 November 2026, an update to its image-generation model that is available globally now in ChatGPT and Codex across all subscription tiers, on desktop, mobile and the web. Two new models, GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst, come to the API at the same time.

GIFs are the headline. With ChatGPT Images 2.6, you can turn a text prompt or an uploaded image into an animated GIF — animating a character or mascot, creating a reaction image or meme, or building a simple storyboard to explore movement before video production. You can adjust the playback speed, edit individual frames, and share the result on repeat. OpenAI’s own example builds a six-frame sprite sheet of a chibi office worker watching a stock-market chart fall, arranged in a 3-by-2 grid. A simple sketch can become an animated character too.

Reference images, saved once. A second addition is reusable reference images: keep images of yourself, your pets and your characters saved and ready to reuse in new creations, without uploading them again. The point is consistency — the same character, product or brand details carried across edits, which has been a weak spot for image models.

Faster, and split two ways for developers. OpenAI says Images 2.6 generates images 50% faster than before — the company’s own performance claim, not an independent test. In the API, Flare is the speed option: when quality is set to low, it can generate images in as little as six seconds, and it also improves layout quality for posters and product imagery. Sunburst is the quality option, aimed at greater detail and greater consistency across edits when quality is set to medium or high. Developers also get image markup in the API, so they can pinpoint exactly where to make a change, SVG exports for designs ready to use across websites, apps and print, and a new complexity parameter that adjusts how much planning the model does for a request.

The scale behind it. OpenAI says people around the world now create 4 billion images per week across ChatGPT, Codex and the API — more than half a billion a day. That volume is the context for the release: image generation is no longer a side feature of ChatGPT, it is one of its biggest workloads, and the GIF and reference-image additions are aimed squarely at the everyday uses — reactions, memes, mascots, product shots — where that volume actually comes from.

Pricing. OpenAI’s published pricing lists both new API models at $8 per million image-input tokens and $30 per million image-output tokens. GIF creation has no separate paywall in ChatGPT, though existing account-level usage caps still apply. OpenAI has also published a system card covering its safety evaluations and safeguards for Images 2.6.

Sources

  • OpenAI
  • ChatGPT
  • Images 2.6
  • GIF
  • image generation
  • Codex

Related articles

AI Tools

How AI Image and Video Generation Works

Type a sentence, get a picture — or a film clip. Here is the idea underneath modern AI image and video generators: diffusion, noise, and why video is the harder problem.

· image generation, video generation, diffusion, explainer