ChatGPT Images 2.6: What's New, GIF Creation, and Alternatives (2026)
OpenAI released ChatGPT Images 2.6 on November 4, 2026. The update makes image generation faster, adds GIF creation in ChatGPT, and keeps reference photos on file for later chats. Developers get two new API models, image markup, and SVG export.
This guide covers what changed, how the new GIF and reference features work, what it costs, and what it means for slides and reports. It ends with alternatives. Every detail comes from vendor pages read on November 5, 2026.
What OpenAI released on November 4
OpenAI's announcement is titled "Introducing Images 2.6." It is dated November 4, 2026. The page says the release brings Images 2.6 to "ChatGPT, Codex, and the API." The ChatGPT release notes carry an entry on the same date.
The main changes are these:
- Faster generation. OpenAI says "Images 2.6 generates images 50% faster than before."
- More consistent edits. The page says you can refine visuals "keeping characters, products, and brand details consistent as you edit."
- GIF creation. You can now ask ChatGPT for a looping animation.
- Saved reference images. You can save a photo once and reuse it in later chats.
- New API controls. Developers get image markup, SVG export, and a new complexity setting.
OpenAI also shares a usage figure. It says people "now create 4 billion images per week across ChatGPT, Codex, and the API." That works out to more than half a billion images a day, by OpenAI's count.
The previous version shipped in September. Our coverage of ChatGPT Images 2.5 explains that release. This page focuses on what Images 2.6 adds.
How GIF creation works in ChatGPT
GIF creation is the most visible new feature. OpenAI's release notes say "GIF creation is rolling out in ChatGPT." So not every account may see it on day one.
The help article "Images in ChatGPT" explains the steps. You ask for a looping GIF and describe what should move. OpenAI's example prompt is "Make a looping GIF of a paper boat bobbing on the water."
You can also start from a still image. Upload it and ask ChatGPT to animate it. The release notes give another example: upload a sketch and ask ChatGPT to make the character wave.
After the GIF is ready, you have a few controls:
- Edit by describing the change. Ask for a different motion or detail in the same chat.
- Change the speed. Open the GIF to adjust its playback speed.
- Download or share. You can save it to your device or share it.
There is one clear limit. The help article states that "ChatGPT can't edit an animated GIF you upload." You can animate a still image, but you cannot revise an existing GIF from another source.
OpenAI pitches the feature at marketers and creators. The page lists uses such as a brand mascot for a campaign and reactions for social media. It also suggests "animated storyboards to explore character movement before video production."
Saved reference images and other ChatGPT features
The second new feature is saved reference images. The release notes say they "let you reuse a photo in later chats."
Here is how it works, according to the help article:
- Upload a photo and ask ChatGPT to save it as a reference.
- Choose a name for it.
- In a later chat, type @ followed by that name in your prompt.
OpenAI's example is a dog photo saved as Pepper. You can then ask for "a watercolor portrait of @Pepper" without uploading the photo again. ChatGPT may also offer to save a photo when you describe one.
For work visuals, this helps with repeat assets. A product shot, a mascot, or a team photo can stay on file across chats.
Several features from earlier releases remain. The help article lists these:
- Templates. Starting points for images such as a poster or logo. The article notes that templates are not yet available in Work mode.
- Sketch on mobile. Type @ in the mobile app, select Sketch, and draw a guide.
- The editor. Select part of an image and describe the change. OpenAI warns that highlights "are not always precise."
- Aspect ratios. Use the picker or name the ratio in your prompt.
Generation is not instant for every request. The help article says image generation "may take a few minutes, depending on the complexity of your request."
What changed in the API
Developers get two models: GPT‑Image‑2.6 Flare and GPT‑Image‑2.6 Sunburst. OpenAI describes them this way:
- Flare is the speed option. "When quality is set to low, Flare can generate images in as little as six seconds." OpenAI adds that Flare improves layout quality for posters and product imagery.
- Sunburst is the detail option. It brings higher quality and "even greater image consistency across edits when quality is set to medium or high."
Three new controls arrive with them:
- Image markup. It is "already available in ChatGPT" and now comes to the API. Teams can mark exactly where an edit should go.
- SVG export. OpenAI says "SVG exports make designs ready to use across websites, apps, and print."
- Complexity. This new parameter sets how much planning the model does for a request. OpenAI recommends low complexity for most editing tasks.
Here are the API prices on OpenAI's pricing page, per 1 million tokens:
| Model | Image input | Image output | Cached image input | Text input |
|---|---|---|---|---|
| GPT-Image-2.6 Sunburst | $8.00 | $30.00 | $2.00 | $5.00 |
| GPT-Image-2.6 Flare | $8.00 | $30.00 | $2.00 | $5.00 |
The page lists the same rates for the 2.5 versions of both models. For cost estimates per image, OpenAI points to a calculator in its image generation guide.
Who can use Images 2.6 and what it costs
OpenAI says Images 2.6 is "available globally today in ChatGPT and Codex across all subscription tiers on desktop, mobile, and web." The help article confirms that ChatGPT Images "is available on all tiers."
One feature is limited by plan. The help article says "Images with thinking is available on Plus, Pro, and Business." Enterprise and Edu are listed as coming soon.
Plan prices on OpenAI's ChatGPT and Codex pricing page, read November 5:
| Plan | Price on OpenAI's page | Images 2.6 |
|---|---|---|
| Free | $0/month | Yes |
| Go | $8/month | Yes |
| Plus | $20/month | Yes, plus images with thinking |
| Pro | From $100/month (tiers at $100, $200, or $500) | Yes, plus images with thinking |
| Business | $20 per user per month billed annually, or $25 billed monthly | Yes, plus images with thinking |
OpenAI's pages do not list a fixed number of images per plan. Limits can still apply, so check your own account if you plan heavy use.
What Images 2.6 means for slides and reports
Most coverage of Images 2.6 will focus on GIFs and social content. For people who build decks and reports, three changes matter more.
Consistent visuals across a deck. A deck often needs the same product, mascot, or character on several slides. Images 2.6 aims to keep those details steady through edits. Saved reference images let you reuse the same photo without uploading it each time.
Motion where it helps. A short loop can show a process step or a product in use. GIFs can sit on a slide or in an email update. Use them sparingly, since motion pulls attention from your numbers.
Cleaner files for print and web. SVG export in the API gives designers scalable files. Better layout quality from Flare helps with posters and title slides.
What Images 2.6 does not do is read your data. An image model draws what you describe. It does not open your spreadsheet, total a column, or check that a bar matches a row. For charts tied to real figures, start from the data file instead. Our guide on adding AI images, graphs, and infographics to slides covers how to combine the two.
Limits to keep in mind
A few points are worth checking before you rely on the new features:
- GIF creation is still rolling out. The release notes use the words "rolling out," so access may vary by account.
- Uploaded GIFs cannot be edited. You can only edit GIFs that ChatGPT created.
- Selections are not exact. The editor's highlights can spill beyond the area you chose.
- Templates skip Work mode. The help article says templates are not yet available there.
- API cost depends on tokens. Prices are per 1 million tokens, so cost per image varies with size and quality.
OpenAI publishes a system card for Images 2.6 with its safety evaluations. Teams with brand or legal review should read it before rolling the tool out.
Alternatives to ChatGPT Images 2.6
Several tools cover the same ground. Each one fits a slightly different job. Prices come from each vendor's page on November 5.
| Tool | Best for | Price, per the vendor |
|---|---|---|
| ChatGPT Images 2.6 | Fast image edits, GIFs, and reusable reference photos | Free plan; Plus $20/month; Pro from $100/month |
| Gemini app | Image generation inside Google's assistant and apps | Google AI Plus $4.99/mo; Google AI Pro $19.99/mo |
| Figma Weave | Node-based creative workflows that mix several models | Paid plans listed on its pricing page |
| Powerdrill Bloom | Charts, infographics, and slides built from your data files | Free plan; Pro $13.27/mo |
Gemini app. Google's plan page says Google AI Plus gives "More access to image, music, and video generation models in Gemini and Search." Google AI Pro expands that access further.
Figma Weave. Figma Weave is adding the new model. OpenAI quotes its creative director saying, "We're excited to add it to Figma Weave." It suits design teams that want repeatable creative workflows. Check its pricing page for current plan terms.
Powerdrill Bloom. This is the data-first option, covered in the next section.
Where Powerdrill Bloom fits
Powerdrill Bloom works from the other end. You start with an Excel, CSV, or PDF file, and the visuals come from your numbers.
The AI Infographic Generator page says you can "Upload Excel, CSV, or PDF—or just input a topic." It adds that Bloom "automatically explores, analyzes, and visualizes your data." The homepage says "Every number comes back with the page, the row and the figure behind it."
It also makes images. The AI Image Generator page describes text-to-image creation, and Pro lists Nano Banana images.
A practical split looks like this. Use ChatGPT Images 2.6 for the cover art, mascot, or a short GIF. Use a data tool for the charts and the summary slides. The pricing page lists a Free plan at $0.00 and Pro at $13.27/mo. Free includes "Create basic slides, docs, sheets, and images."
Try Powerdrill Bloom with the data behind your next deck.
Frequently asked questions
What is ChatGPT Images 2.6?
It is OpenAI's image generation update released on November 4, 2026. OpenAI says it generates images 50% faster than before. It adds GIF creation and saved reference images in ChatGPT, plus new API models.
How do I make a GIF in ChatGPT?
Ask for a looping GIF and describe what should move. You can also upload a still image and ask ChatGPT to animate it. Open the GIF to change its playback speed, save it, or share it.
Is Images 2.6 free?
Yes. OpenAI says it is available across all subscription tiers, including Free. Images with thinking is limited to Plus, Pro, and Business. GIF creation is still rolling out.
What are saved reference images?
They keep a photo on file so you can use it again in later chats. You name the photo, then type @ followed by the name in a new prompt.
Can Images 2.6 make charts from my spreadsheet?
OpenAI describes Images 2.6 as an image model, not a data tool. It draws what you describe. For a chart built from your own rows, use a tool that reads the file.
Sources: OpenAI, Introducing Images 2.6 · ChatGPT release notes · OpenAI Help, Images in ChatGPT · OpenAI API pricing · ChatGPT and Codex pricing · Images 2.6 system card · Google AI plans · Figma Weave pricing. Details read from vendor pages on November 5, 2026.