Newegg product image requirements and what to ask Sume for

What are Newegg's product image requirements?

Newegg's Seller Academy page lists a 640 pixel width, a 480 pixel height and a file size of no more than 5 MB as the size limits, and asks for clear, borderless images with no watermarks, logos or extra text. It prefers a white background, forbids collages on the primary image, and bans real persons, body parts or models there.

The page frames the three size numbers as criteria an image has to meet, so the safe plan is to deliver all three: at least 640 by 480 pixels and at most 5 MB. Everything below is what the page says; the Sume half of this post covers what you can ask the Image API for.

Newegg's rules in one table

The table restates the policy page without adding anything to it. Rules that Newegg words as a preference (the background) are marked as such.

Which Sume model fits a white-background primary image?

The Sume Image API accepts a catalog id on POST /v1/images. For a clean primary image from a reference photo, ChatGPT Image 2.5 (openai/gpt-image-2.5) takes up to 16 image references and has a background parameter with the values auto, transparent and opaque. Its quality ladder is auto, low, medium, high, xhigh and max, and an omitted quality defaults to high.

Custom pixel sizes on this model need both edges to be multiples of 16, with a maximum edge of 3840, an aspect ratio of at most 3:1 and between 655,360 and 8,294,400 pixels in total. That matters for Newegg: 640 by 480 is 307,200 pixels, which is below the Sume floor, so a 640 by 480 custom size is not an accepted request. A 1024 by 1024 image is 1,048,576 pixels, passes the floor, and clears Newegg's 640 by 480 minimum on both edges.

What to ask Sume for

Ask for a square or near-square product shot, one product, an opaque background and a PNG or JPEG. Keep the prompt strict about the rules Newegg lists: no text, no logos, no watermark, no person. Then check file size yourself, because the Image API response gives you a URL and a media type, and the 5 MB limit is Newegg's to enforce.

``json { "model": "openai/gpt-image-2.5", "prompt": "Product only, centered, plain white background, no text, no logo, no watermark, no person", "input_references": [{"type": "image_url", "image_url": {"url": "https://example.com/product.jpg"}}], "quality": "high", "background": "opaque", "output_format": "jpeg", "n": 2 } ``

n accepts up to 10 per call on the API page, with per-model ceilings lower, so read the n range descriptor on the catalog row before pinning it. Sume does not guarantee a white background from a prompt, so open each result before you upload.

What Sume cannot decide for you

The Newegg page says every image must be the actual image of the product. A generated background swap on a real reference photo keeps the product as shot, while a text-only render of an item you have not photographed would not satisfy that rule. Use references of the real item, and use n to compare a couple of variants.

For the exact size, see the Image API docs; for a pipeline view of white-background work, see AI product photo, white background to lifestyle scene.