Introducing GPT Images 2.5 in the API and ChatGPT

Announcements
, ,
1

ChatGPT Images 2.5—faster, sharper, smarter, with better tools for creating whatever you can dream of.

  • Faster image generation to keep your ideas flowing

  • Improved fidelity for more natural, recognizable images

  • Consistent details across multiple edits

  • Comment-based edits to change only what you want

Some ideas are easier to draw than describe.

Use Sketch to draw right in ChatGPT and show it exactly what you have in mind.

Just type “@ Sketch” in ChatGPT.

Have an idea but need help getting started?

Use templates for popular image formats like posters or merch, then add your message, design elements, or style to make it your own.

ChatGPT Images 2.5 is rolling out today to all ChatGPT, ChatGPT Work, and Codex users across desktop, mobile, and web.

We’re also introducing two new models in the API: GPT-Image-2.5 Flare brings the same quality, editing, and speed improvements, while GPT-Image-2.5 Sunburst adds precision for detailed creative work, with longer generation times.

3

Cost per token seems to have remained the same as gpt-image-2 - but we don’t know how many tokens these new models will consume in comparison?

4

Can it be better, in ChatGPT Work using both Astra and ChatGPT images 2.5? Well here’s the first taste.

image
image1254×1254 434 KB

5

If using ChatGPT, and using reasoning effort, you might observe an image generated - and then a “retry” or an edit. I’ve had this happening already in days past. One image is shown - that you have to copy and save fast. Then it is replaced irrecoverably. Attempts to curb this fail:

image
image648×185 3.97 KB

Or result in confusion:

image
image635×161 4.06 KB

It may be reasoning model “agentic” behavior attempting to loop and “improve” - but the edit based on image input is worse.

Using “instant”, this does not seem to happen. There’s a progress percentage indicator now you can watch.

API is the same token pricing as gpt-image-2.

However, the actual token usage of input and output is completely undocumented when they included this model only briefly in the image generation page. gpt-image-2.5 pricing is distinctively not reusing the calculator they supplied for gpt-image-2 output, nor is its input (nor gpt-image-2 costs) anywhere in the vision calculator that is finally updated through gpt-5.6 (and not Astra).

“Flare” has 50% lower latency - but the same token cost. I expect “Sunburst” to be billing its “premium visual workflows” in more usage.

6

Further API rollout:

  • No batch pricing (no batch support checkbox in model page)
  • No API token limits by tier shown in the model pages
  • (Don’t have them yet on API models endpoint, so my lack of platform org limits are expected.)
7

This GitHub update may be of interest.

8

Super useful, thank you! So they introduce xhigh and max for this one.