Reported News

OpenAI Images 2.6: GPT-Image-2.6 Flare and Sunburst add GIFs, SVG export and a complexity control

OpenAI released Images 2.6 on November 4, 2026 in ChatGPT, Codex and the API, where it ships as gpt-image-2.6-flare and gpt-image-2.6-sunburst. OpenAI says it "generates images 50% faster than before" and adds animated GIFs, SVG output, markup-guided edits and a new complexity setting, at $30 per 1M image-output tokens.

Share on X
Changes reported
6
listed below, each from a source we read
We tested
Not tested yet
reported from sources; we did not run it ourselves
Gaps we flag
4
things we could not verify
Sources
5
5 primary, linked below

What changed

Changes the sources report, with the evidence status of each
#What the source saysStatus
01Launch: Images 2.6 is available globally in ChatGPT and Codex on all subscription tiers (desktop, mobile and web), and in the API as two models, GPT-Image-2.6 Flare for fast iteration and GPT-Image-2.6 Sunburst for detailed work.Reported
02Speed: OpenAI says Images 2.6 generates images 50% faster than before, and that Flare at low quality can return an image in as little as six seconds. Sunburst is pitched for higher quality and more consistent edits at medium or high quality.Reported
03New output types: animated GIFs (for example looping mascots or reaction images) and SVG export, both available through the Image API for Flare and Sunburst, per OpenAI's image generation guide.Reported
04New complexity request field (low, medium, high; high if omitted) controls how much the model plans before rendering, separately from quality. OpenAI recommends low complexity for most edits and says adjusting it has no separate fee.Reported
05Image markup, already in ChatGPT, comes to the API: markup-guided editing works on supported GPT Image 2.5 and 2.6 models, per the Nov 4 API changelog.Reported
06API details: both models take text and image input, output images, and support only v1/images/generations and v1/images/edits; the model pages list Batch and the Responses API as not supported. Price is $5 per 1M text input tokens, $8 image input and $30 image output.Reported

reported by the sourcemeasured or run by usnot verified

Primary source: OpenAI: Introducing Images 2.6 (Internet Archive capture; openai.com blocks scripted fetches). We are the fast, independent index; the vendor’s own page is the source of record for this release.

In the source’s words

“Images 2.6 generates images 50% faster than before.”

“When quality is set to low, Flare can generate images in as little as six seconds.”

“Adjusting complexity has no separate fee.”

What we have not verified

  • We did not run Images 2.6; the 50% speed gain and six-second figure are OpenAI's claims, and the post does not say what "before" is measured against.
  • OpenAI's post and feed give only the date (November 4, 2026), so the exact release time is unknown; the Internet Archive captured the post at 23:36 UTC that day.
  • Per-image costs depend on token counts we did not measure; the model pages give token prices only and say rate limits vary by account.
  • Whether Batch or the Responses API image tool will add 2.6 later is not stated. We did not read the system card linked from the post.

This brief is Reported: written from the sources below, not from running the release ourselves.

Sources

Spotted an error? See our corrections policy or email the address on the contact page. Markdown version for agents: /news/openai-introducing-images-2-6.md

Want these briefs in your Google Top Stories? Add Agentic Weekly as a preferred source on Google.

Newsletter

The Weekly Verdict. Free, every Monday.

A free email every Monday: the week's few big AI releases, then 5 short use cases for the new models, each with a prompt you can paste.

Free. Double opt-in. One click to unsubscribe.