bol.com product image requirements and what to ask Sume for
bol's Partner Platform image rules (500 to 6000 px, 30 KB to 10 MB, white main image, 1200 px zoom) and the Sume Image API request that fits.

What are bol.com's product image requirements?
bol's Partner Platform asks for images of at least 500x500 pixels and at most 6000x6000, between 30 KB and 10 MB, with a white, neutral background and no visible shadows on the main image. The zoom function needs at least 1200x1200 pixels, so 1200 px is the practical target.
One detail matters for generated images: bol says white space does not count towards the stated minimum and maximum pixels. A 1200x1200 canvas with a small product in the middle may not give you the zoom bol describes, so let the product fill the frame.
| Rule | What bol's page says |
|---|---|
| Pixel size | At least 500x500, at most 6000x6000 |
| Zoom | Works with images of at least 1200x1200 |
| File size | At least 30 KB, at most 10 MB |
| Main image background | White, neutral, no visible shadows |
| Main image content | Item out of its packaging (board games and media carriers excepted); no models, text, statements, logos, icons or watermarks; front of the item |
| Other images | Different perspectives and relevant details; same pixel and file-size rules; lifestyle photos allowed here |
| Never in any image | Discount labels, company names, promotional text such as 'buy now', service claims such as warranty or shipping |
How should the Sume request look?
Use openai/gpt-image-2.5 on POST /v1/images. Per the Image API docs it accepts references (up to 16), background: auto|transparent|opaque, and custom pixels where both edges are multiples of 16. 1200 is 75 x 16, and 1200x1200 is 1,440,000 pixels, inside the documented 655,360 to 8,294,400 range.
Pass your own packshot as a reference and ask for the same product, unchanged, on white. The prompt is where you say 'no text, no logo, no shadow'; Sume does not enforce bol's rules for you.
curl -X POST https://api.sume.com/v1/images \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-image-2.5",
"prompt": "Same product, unchanged, centred and filling the frame, plain white background, no shadow, no text, no logo",
"input_references": [{"type": "image_url", "image_url": {"url": "https://example.com/packshot.png"}}],
"image_size": "1200x1200",
"quality": "high",
"background": "opaque",
"output_format": "jpeg",
"n": 1
}'Which Sume fields map to which bol rule?
Quality defaults to high on this model when omitted; auto|low|medium|high|xhigh|max are the listed values. Image 2.5 reserves max for auto, so pin a tier if you want a predictable cost.
n takes 1 to 4 on most image models according to the catalog, so a gallery of several perspectives is a few calls, each with its own prompt for angle.
| bol rule | Sume field | Value |
|---|---|---|
| Zoom at 1200x1200 | image_size | 1200x1200 |
| White main image | background plus prompt | opaque, 'plain white background' |
| Product unchanged | input_references | Your packshot URL |
| Finals | quality | high |
| Several perspectives | n and one prompt per angle | 1 to 4 per call |
What should you still check by hand?
Download the file and check what bol checks: pixel size, the 30 KB floor and 10 MB ceiling, and that the product, not padding, fills 1200 px. bol's developer news from 10 February 2022 says images below 500x500 return the error 'file's resolution is too low (min 500 x 500 pixels)', so a rejected upload tells you which side to fix.
Do not let a model add a packaging box, a badge or a lifestyle scene to the main image; bol keeps lifestyle for the additional images only.
Sources
Related posts
More in Use cases
- Burn captions on a silent product video with authored cues
A silent clip fails Sume captioning with caption_no_speech. Pass cues or segments with text, start and end to burn your own copy, no transcription step.
- Burn the same required line onto 50 product clips with Sume cues
One cue request per clip puts the same required text on every product video in a batch. Idempotency keys, the 60 second limit, and a $10.00 batch cost.
- Cafe or bakery weekly clips: five photos, five 5-second clips
Animate five product photos into vertical clips with seedance-2.5 first_frame, then join them in Timeline 1.0. What the API accepts and what it can't promise.
- Can a brand make the video for a creator's Meta partnership ad?
Meta's branded content policy says creators cannot be paid to post content they were not involved in making. What that means for brand-made AI clips.
Written by Sume