# Images 2.6 — OpenAI's image model now makes GIFs and SVGs, 50% faster

> OpenAI's Images 2.6 adds motion: sketch a character, get a looping GIF, in ChatGPT or through the API.

- Org: OpenAI
- Date: 2026-11-04
- Category: model, tool
- Source: https://developers.openai.com/api/docs/models/gpt-image-2.6-flare
- Canonical page: https://ai-tldr.dev/releases/openai-images-2-6/

## In short

Images 2.6 is OpenAI's new image model for ChatGPT, Codex and the API. It turns images into animated GIFs, exports SVG, and generates 50% faster. Two API models ship: GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst.

## What it is

Images 2.6 is OpenAI's new image generation model. Its headline addition is animated GIFs: a brand mascot, a reaction meme, a product shot turned into a loop, or a pen sketch turned into a moving character. It also exports SVG, and OpenAI says it generates images 50% faster than before while keeping characters, products and brand details consistent across edits.

## How it works

Developers pick between two API models. GPT-Image-2.6 Flare is built for fast iteration and better layouts on posters and product imagery — at low quality it can return an image in about six seconds. GPT-Image-2.6 Sunburst targets detailed work and holds edits more consistently at medium or high quality. A new complexity field sets how much the model plans before it draws: low for focused edits like swapping a background, high (the default) for dense text and crowded scenes. Image markup, which ChatGPT already had, now works in the API so a request can point at the exact spot to change.

## Why it matters

GIF and SVG output remove an extra tool from common design jobs: a team can animate a mascot or ship a vector asset straight from a prompt. The complexity setting adds no fee, so apps can trade planning for speed per request. People now make 4 billion images a week across ChatGPT, Codex and the API, according to OpenAI, and the startup Town already uses Images 2.6 for an animated typing-indicator character in its work assistant.

## Who it's for

designers, marketers and app developers

## Try it

Call gpt-image-2.6-flare on the Images API with complexity set to low

## Quick facts

- Maker: OpenAI
- API models: gpt-image-2.6-flare and gpt-image-2.6-sunburst
- Availability: ChatGPT and Codex, all tiers, desktop, mobile and web; Images API
- New outputs: Animated GIFs and SVG export
- API price (both models): $8 / 1M image input tokens, $30 / 1M image output tokens
- New API control: complexity: low, medium or high (default high)

## FAQ

### How much does GPT-Image-2.6 cost in the API?

OpenAI's model pages list the same token prices for GPT-Image-2.6 Flare and GPT-Image-2.6 Sunburst: $5 per million text input tokens ($1.25 cached), $8 per million image input tokens ($2 cached) and $30 per million image output tokens. The complexity setting has no separate fee, according to OpenAI's image generation guide.

### What is the difference between GPT-Image-2.6 Flare and Sunburst?

GPT-Image-2.6 Flare is OpenAI's model for fast iteration: at low quality it can generate an image in as little as six seconds, and it improves layouts for posters and product imagery. GPT-Image-2.6 Sunburst is for detailed visual work, with higher quality and stronger consistency across edits at medium or high quality. Both support GIF output, SVG output, markup-guided edits and complexity control.

### Can ChatGPT Images 2.6 make GIFs on the free plan?

OpenAI says Images 2.6 is available globally today in ChatGPT and Codex across all subscription tiers, on desktop, mobile and web, and that it can animate images into GIFs. The announcement does not publish per-plan limits on how many images or GIFs each tier can create.

### What does the complexity parameter do in GPT-Image-2.6?

The complexity field in the GPT-Image-2.6 API sets how much the model plans before it renders. It accepts low, medium or high and defaults to high. OpenAI suggests low for focused edits such as changing a background or a sign, and medium or high for dense text, complex layouts and many objects; higher settings can add latency.

## Links

- [Flare Model Page](https://developers.openai.com/api/docs/models/gpt-image-2.6-flare)
- [Sunburst Model Page](https://developers.openai.com/api/docs/models/gpt-image-2.6-sunburst)
- [Image Gen Guide](https://developers.openai.com/api/docs/guides/image-generation)
- [API Pricing](https://developers.openai.com/api/docs/pricing)
- [HN Discussion](https://news.ycombinator.com/item?id=50372945)