One of the two selectable GPT Image 2.5 products on this platform: text and reference-based image generation with transparent-background support at the 1K tier.
Flare and Sunburst are two separately selectable products in the GPT Image 2.5 family. In our workspace they expose the same controls and the same credit prices, and we do not claim that one outperforms the other. They are variants to choose between and compare on your own prompts.
This page concentrates on transparent backgrounds and reference-heavy work, which are the controls that set this family apart from the text-only image models on the platform.
Choose a quality tier (1K, 2K or 4K), a shape and, at 1K, a background setting. Background control is a 1K option: leaving it on automatic keeps 2K and 4K available.
At 1K you can request a transparent background explicitly. Check the finished file before relying on it in a layout; that check is what tells you whether any hand-touching is still needed.
Supply a set of images such as products, characters or layouts and describe how they should combine in one render.
Choose among thirteen shapes. The 27:16, 16:27, 9:8 and 8:9 options require the 1K tier.
Generate a subject with the transparent-background setting, then inspect the edges before placing it into a page or composition.
Use the extended shape list for headers and placements that standard square or 16:9 output does not fit.
Combine several supplied references, such as a product and its packaging, into one scene.
Use a button on this page. It opens the right workspace with this model already selected, in the language you are reading now.
Write what should happen in the shot or image. Concrete subjects, framing and action give the model more to work with than short labels.
Choose length or quality tier, shape and sound where offered, then read the credit quote for those exact settings before you generate.
Generation uses account credits. Cost depends on the model, quality and output size or duration. Reference images, video or audio may add charges in some modes. Check the workspace quote for your selected inputs and settings before generating; the pricing page lists credit packages.
See credit packagesThey are two selectable variants of the same GPT Image 2.5 family. Our workspace offers identical controls and identical credit prices for both, and we have no evidence that one produces better results than the other.
You can request one at the 1K tier by setting the background control explicitly, then check the finished file before relying on it. Leaving the control on automatic keeps the 2K and 4K tiers available.
Up to sixteen in one editing task.
No. The tier names describe a quality setting rather than a guaranteed pixel size, and the measured dimensions of a finished file depend on the shape you chose.
Per image, by quality tier. The exact credit amount for your settings is shown in the workspace before you confirm.
Other models on this platform that do a similar job, or that pair well with this one.
The second selectable GPT Image 2.5 product: the same tiers, shapes, background control and credit prices as Flare, with this guide focused on editing your own images.
Read the guideNano Banana 2.1 covers both workflows on one model: images from a description, or edits driven by up to ten of your own reference images, at 1K, 2K or 4K.
Read the guideThe FLUX 3 family product available on this platform: text generation and reference editing at 1K, 2K or 4K, with PNG, JPEG and WebP output.
Read the guide