- OpenAI's most capable GPT Image model
Position
- Up to 10, with optional mask
Input images
- Low, medium, high, xhigh, max
Quality levels
- 3840px edge, 1:3 to 3:1
Max size
- 1 to 4
Images per request
About GPT Image 2.5 Sunburst
GPT Image 2.5 Sunburst is OpenAI's most capable model for image generation and editing. OpenAI recommends it for workflows where editing precision matters most, which is exactly where business creative gets difficult: changing one element of an approved image without disturbing the rest, placing a real product into a new scene, or updating a layout that already carries brand text. Sunburst accepts text and image inputs, supports inpainting through OpenAI's edit endpoint, and offers five quality levels from low to max, including the xhigh and max settings that earlier GPT Image models do not have.
In Masonry, Sunburst is the default image model. It runs on OpenAI's own API, takes up to 10 input images per request with an optional mask, generates one to four images at a time, and accepts any size OpenAI allows, up to 3840 pixels on the long edge with aspect ratios from 1:3 to 3:1. Its sibling, GPT Image 2.5 Flare, is OpenAI's faster model for everyday generation. Masonry charges both the same at the same quality and size, so the choice between them is about the job: Flare for quick options from a text prompt, Sunburst for edits, reference-driven work, and finished deliverables.
Why teams choose GPT Image 2.5 Sunburst
Choose GPT Image 2.5 Sunburst when the image has to be right rather than merely fast. OpenAI positions it as its most capable model for generation and editing and recommends it where editing precision matters most, which covers most finished business deliverables, edits to approved images, and work that must keep an uploaded product, person, or logo faithful. Flare is OpenAI's faster sibling and costs the same in Masonry, so use it for quick text-only options and move to Sunburst for the keeper. GPT Image 2 remains available if a workflow is tuned to it, but it stops at high quality while Sunburst adds xhigh and max. Nano Banana Pro is a strong alternative for top-end hero images.
What GPT Image 2.5 Sunburst can do
The capabilities that set GPT Image 2.5 Sunburst apart and earn its place in a brief
Built for Editing Precision
OpenAI positions Sunburst as its most capable model for generation and editing, and recommends it where editing precision matters most. Use it to swap a background, change a color, replace a prop, or update copy on an image you have already approved.
Up to 10 Input Images
Add up to 10 images to a request in Masonry to edit or reference. Supplying any image switches the request to OpenAI's edit endpoint, so a product shot, a logo, and a style reference can all inform one result.
Masks for Targeted Changes
Add an optional mask to mark the area to change. With several input images, the mask applies to the first one. OpenAI notes that masking is prompt-based, so pair the mask with a clear description of the edit.
Five Quality Levels, Up to Max
Choose low, medium, high, xhigh, or max. The GPT Image 2.5 models add xhigh and max above the high ceiling of earlier GPT Image models. Masonry defaults to low, so explore at low and raise quality for the final render.
Any Size Up to 3840 Pixels
Masonry offers presets at 1K, 2K, and 4K for 1:1, 4:5, 5:4, 3:4, 4:3, 2:3, 3:2, 9:16, and 16:9, and accepts any custom size OpenAI allows. Edges are multiples of 16, the long edge tops out at 3840 pixels, and ratios run from 1:3 to 3:1.
Transparent Backgrounds
Set the background to transparent to get a PNG with no backdrop, ready for product pages, packaging mockups, decks, and ad templates. Auto and opaque are the other options.
Where teams reach for GPT Image 2.5 Sunburst
- Product-in-scene photographySupply a real product photo and describe the scene, so the product appears in a lifestyle or studio setting without a reshoot. Check labels and fine detail against the source before publishing.
- Targeted edits to approved imagesChange the background, color, prop, or season of an approved hero image while asking the model to keep everything else as it is.
- Brand sets from referencesUse a logo, palette, and product photos as input images to build a consistent set of ads, carousels, or social posts.
- Layouts with textPosters, ad frames, UI mockups, and infographics where headlines and labels must be spelled exactly. Quote every string in the prompt.
- Packaging and label mockupsPlace artwork on a package or bottle, then refine with edits until the composition is ready for review.
- Transparent cut-outsGenerate isolated products and objects as transparent PNGs for marketplaces, decks, and templates.
- Finishing a pick from FlareExplore options quickly on GPT Image 2.5 Flare, then continue on Sunburst with the chosen image as input for the edits and final render.
Frequently asked questions
What teams need to know about creating with GPT Image 2.5 Sunburst in Masonry
What is GPT Image 2.5 Sunburst?
GPT Image 2.5 Sunburst is OpenAI's most capable model for image generation and editing. It accepts text and image inputs, produces images, and supports generation and inpainting. Masonry calls it through OpenAI's API and uses it as its default image model.
Should I use GPT Image 2.5 Flare or Sunburst?
Use Flare when speed matters, since OpenAI describes it as its fastest model for high-quality, everyday image generation. Use Sunburst when quality and editing matter, since OpenAI describes it as its most capable model for generation and editing and recommends it where editing precision matters most. In Masonry both cost the same at the same quality and size, so a common pattern is to explore options on Flare and finish on Sunburst.
How does GPT Image 2.5 Sunburst compare with GPT Image 2?
OpenAI says the GPT Image 2.5 models add xhigh and max quality settings, while earlier GPT Image models stop at high. In Masonry, Sunburst also exposes a background setting for transparent output. Both share OpenAI's custom-size rule and accept up to 10 input images in Masonry.
Can GPT Image 2.5 Sunburst edit an existing image?
Yes. Add one or more input images, up to 10 in Masonry, and the request goes to OpenAI's edit endpoint. Describe what should change and what should stay the same. You can add a mask to mark the area to change, and with several input images the mask applies to the first one.
How do masks work with GPT Image 2.5 Sunburst?
A mask marks the region of the first input image you want changed. OpenAI notes that masking with GPT Image is prompt-based, so the mask guides the edit rather than acting as a hard boundary. Describe the change clearly in the prompt as well.
How many reference images does GPT Image 2.5 Sunburst accept?
Up to 10 input images per request in Masonry. They can be images to edit or references such as a product shot, a logo, or a style example.
Can GPT Image 2.5 Sunburst keep my real product accurate?
Sunburst is the GPT Image 2.5 model OpenAI recommends for precise editing, and it is the better choice of the two when an uploaded product has to stay faithful. No image model guarantees exact reproduction, so compare the shape, color, and label text against your source before publishing.
What sizes and aspect ratios does GPT Image 2.5 Sunburst support?
Any size where width and height are multiples of 16, the long edge is at most 3840 pixels, the ratio is between 1:3 and 3:1, and the total is between 655,360 and 8,294,400 pixels. Masonry offers 1K, 2K, and 4K presets for nine common ratios. OpenAI notes that sizes above 2560x1440 are experimental.
What quality settings does GPT Image 2.5 Sunburst have?
Low, medium, high, xhigh, and max. Masonry defaults to low. Higher settings use more output tokens and take longer, so they cost more credits per image.
Can GPT Image 2.5 Sunburst make transparent PNGs?
Yes. Set the background to transparent and the output is a PNG with no backdrop. The other background options are auto and opaque.
How good is GPT Image 2.5 Sunburst at text in images?
Put every exact string in quotation marks with its position, and the model can render headlines and labels for ads, posters, and layouts. OpenAI notes the GPT Image models can still struggle with precise text placement and clarity, so proofread every word before an image ships.
How many images can GPT Image 2.5 Sunburst generate at once?
One to four per request in Masonry, which makes it easy to compare a few versions of an edit or a scene before choosing one.
What is the best way to prompt GPT Image 2.5 Sunburst?
For edits, state the change first and then everything that must stay the same. For product scenes, describe the setting, light, and camera, and ask the model to keep the product exactly as in the source. Quote any on-image text, explore at low quality, and raise quality for the final render.
How does my team use GPT Image 2.5 Sunburst in Masonry?
Open a Masonry canvas, pick GPT Image 2.5 Sunburst from the model selector, and describe the image you need: a product shot, an ad creative, a social post. Masonry generates it, then you refine, edit, and combine GPT Image 2.5 Sunburst with other models in one workspace.
Is GPT Image 2.5 Sunburst free to try?
New Masonry accounts get 50 free credits to try GPT Image 2.5 Flare. GPT Image 2.5 Sunburst is included in every paid plan, and the editor shows the exact credit cost before you generate.
How do I write good prompts for GPT Image 2.5 Sunburst?
For an edit, say what should change and what must stay the same, in that order, and name the input image each instruction refers to when you supply several. For a product placed into a new scene, describe the scene, lighting, and camera angle, and ask the model to keep the product's shape, color, and label exactly as in the source. Put every on-image string in quotation marks with its position. Explore at low quality, then raise quality for the frame you will ship, and always compare fine detail such as label text against the source.
Who makes GPT Image 2.5 Sunburst?
GPT Image 2.5 Sunburst is built by OpenAI. Inside Masonry it runs alongside 50+ image and video models, so your team can pick the right one for each brief without switching tools.
Start creating with GPT Image 2.5 Sunburst
Generate, edit, and compare across 50+ models in one workspace.
Guides for GPT Image 2.5 Sunburst
Prompt walkthroughs and examples from the Masonry blog
Explore more AI models
Compare GPT Image 2.5 Sunburst with other models teams run in Masonry