GPT Image 2.5 Sunburst:official is an image generation and editing endpoint focused on high fidelity and fine-grained control. It can create new visuals from text or use reference images to adjust backgrounds, objects, and visual details, making it suitable for product assets, campaign key visuals, and iterative revisions of existing designs. Compared with Flare, which emphasizes speed, Sunburst is better suited for tasks that require attention to modification requests and preserving details.
Submit requests to the public API at api.acedata.cloud using the documented parameters, then use the results in your application.
Input parameters and result formats vary by service. Use the public API for this model and follow its guide for generation, task retrieval and editing operations.
Sunburst is positioned for high fidelity and fine-grained control. The quantity, format, and size rules above correspond to this platform's actual API endpoint.
When editing, you can submit images and text requirements at the same time, separately explaining “what needs to change” and “what needs to be kept.” When changing a product background, modifying props, or adjusting lighting, clearly specify the subject’s shape, color, labels, and composition requirements so revisions build on the existing visual rather than redesigning the entire image each time.
When you need to focus edits on a specific area, upload the original image together with an Alpha PNG mask: transparent areas may be edited, while non-transparent areas indicate what should be retained. The prompt should still describe the complete target image and clearly specify local changes. Masks are suitable for replacing background elements or correcting objects, but edge blending should still be checked after completion.
For consecutive edits, you can use the image selected in the previous round as the reference for the next round, handling backgrounds, lighting, and object details in sequence. Save confirmed versions in each round to prevent later changes from affecting previously approved parts. Generated results can be integrated into applications via image URL or Base64, and longer tasks can also return completed results through callbacks.
Input product photos, descriptions of the target environment, and packaging details that need to be retained to create studio, holiday, or lifestyle assets. Background areas can be constrained with masks, then check the product outline, labels, and shadows. Deliverables are suitable for creative review; if product pixels must remain completely unchanged, retain the original product and use compositing instead.
Provide the selected key visual and brand references, specify the new scene, props, whitespace, and copy placement, and create revisions around the existing concept. This is suitable for tasks where the design direction has already been determined and only several visual elements need to change. Before delivery, check brand colors, text content, and layout item by item, and avoid treating generated drafts directly as final print files.
Use the selected concept image as a reference, list the required changes to objects, backgrounds, and local details, and complete targeted revisions over multiple rounds. You can first use Flare to explore visual directions, then use Sunburst for detailed revisions. Focus on clearly defined goals in each round, output candidate images and retained versions, and make it easier for designers to compare and choose.
When you need to quickly explore composition, style, and creative directions, prioritize the speed-focused GPT Image 2.5 Flare; when you already have reference images and the requested changes are focused on products, brand elements, or local details, Sunburst is more suitable. The trade-off between the two should be based on the task stage, rather than treating Sunburst as an option that is necessarily better for every generation task.
gpt-image-2.5-sunburst:official and the suffix-free Sunburst share the same basic creative positioning; the suffix does not indicate a new image version. This endpoint is billed based on the actual Token usage of text input, reference image input, and image output, while the suffix-free endpoint is billed by the number of successfully generated images. Explicitly provide the full ID when calling it, and save the parameters used for easier reproduction and comparison.
Provide prompt when generating; provide both image and edit instructions when editing. Clearly specify the original text, subject preservation requirements, and target aspect ratio.
Call the image generation or image editing endpoint and explicitly specify model=gpt-image-2.5-sunburst:official; use auto or WIDTHxHEIGHT for size, and generate one image before evaluating. Set masks, quality, and file format according to this endpoint guide.
Read the URL or Base64 image according to the response format, asynchronously save task_id before querying the result; check text, reference details, and the alpha channel, and record usage according to the current Pricing rules.
Make local revisions to the reference brand visual: add only a beam of soft light at a specified position in the background, while preserving the people, product, text, and composition, with no change to the overall color temperature.
When a region mask is needed, use multipart according to this public variant guide; verify the mask first, then compare results. Billing is based on actual usage and current rules.
Yes. Text-to-image generation uses /openai/images/generations, while modifications to existing images use /openai/images/edits. The former submits a description and the full model ID, while the latter also requires the original image. Reference-image editing can be used to change backgrounds, modify props, and adjust details, rather than merely regenerating a similar image.
Use the product photo as a reference, and clearly list the outline, colors, labels, and composition to preserve, while limiting the background or objects that need to be changed. Local edits can be used with masks, but pixel-perfect preservation cannot be guaranteed; if the original product must remain completely identical, it is recommended to generate the environment first and then composite it with the original product.
This is determined by the Alpha channel: transparent pixels with an Alpha value of 0 indicate areas that may be edited, while non-transparent pixels indicate areas that should be preserved; it is not determined by black-and-white colors. The mask must be a PNG no larger than 4MB and have the same dimensions as the first original image; the original image and mask need to be uploaded together via multipart.
The editing endpoint supports up to 16 reference images, submitted using a URL array or multiple multipart image fields. The generation count n supports 1–10; if b64_json is selected as the response format, only 1 image can be generated. When using multiple input images, explain the role of each reference image in the prompt to reduce ambiguity about the target.
No. This endpoint is billed based on the actual Token usage of text input, reference-image input, and image output, and prices before a request are estimates. Size, quality, reference images, and generation count all affect usage. When evaluating the cost of a complete revision task, multiple rounds of revisions should also be included, rather than considering only the initial generation.
Choose a development approach or application suited to this model and follow its setup guide.
↗Python SDK Integration Guide
SDK installation, authentication and examples↗TypeScript SDK Integration Guide
SDK installation, authentication and examples
↗↗Pricing
$0.004–$0.17· per generation
You pay$13,584for 142,800 credits · $0.0951 / credits46% OFF
Billed on actual usage
You're billed in credits. Pick a top-up tier to see its per-credit rate — the larger the top-up, the cheaper each credit.
This is only a basic call example. See the full docs for more parameters and advanced usage.
View Docs