Background removal that bills per image, not per seat.
Send a URL or a base64 image. Get a transparent PNG back. There is no editor to log into, no monthly minimum, and no separate subscription for the one step of your pipeline that needed a cutout.
One required field
The whole surface is image. Everything else is optional. That matters more than it sounds: a tool an agent can call correctly on the first try is a tool that actually gets used mid-task.
imagehttps URL or base64 data URI. imageBase64 works as an alias.responseFormat"url" by default; "b64_json" adds the raw bytes.modelOptional override if you have been given a specific matting model.
# REST
curl -X POST "https://api.imagemcpserver.com/playground/remove-background" \
-H "Authorization: Bearer $IMAGEMCP_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "image": "https://cdn.example.com/shoe.jpg" }'
# From an agent, via MCP
{
"name": "remove_background",
"arguments": { "image": "https://cdn.example.com/shoe.jpg" }
}Where a cutout is the difference between shipping and not
Catalogue imports
Suppliers send photos on beige carpet, grey studio walls and kitchen tables. One pass over the import queue and every product sits on the same clean ground.
Composites
A cutout can be dropped onto a gradient, a lifestyle photo or a colour block. A JPEG with a baked-in background can only ever be a rectangle.
Marketing layouts
Subjects that break out of their container — overlapping a heading, bleeding past a card edge — need alpha. This is the call that gets you there.
User-generated content
Profile pictures and submitted photos arrive with whatever was behind the person. Normalising them makes a directory look designed rather than assembled.
Sprite and icon work
Game and app assets need transparency by definition. Generate, cut out, then upscale, and the whole set comes off one pipeline.
Print and packaging
Cut out first, upscale second. Doing it the other way round means upscaling background you are about to throw away.
Three tools touch transparency. Pick the right one.
| You have… | Use | Cost |
|---|---|---|
| A photo that needs its background gone | remove_background | 8 credits |
| Nothing yet — you need the subject made and cut out | generate_transparent_image | model + 8 |
| A photo needing a new background, not no background | edit_image | ~10 credits |
Background removal API questions
What format does the cutout come back in?
A PNG with a real alpha channel, hosted on Cloudflare R2 and returned as an https URL. Pass responseFormat: "b64_json" to also get the base64 bytes in the same response.
Does it handle hair, fur and semi-transparent edges?
The matting model produces soft alpha rather than a hard binary mask, which is what makes hair and glass edges usable rather than jagged. Busy backgrounds that share the subject’s colour are still the hardest case for any matting model, including this one.
How much does each removal cost?
A flat 8 credits, whatever plan you are on. Background removal runs on our own provider account, so it is priced the same with or without your own OpenRouter key connected.
Can I remove backgrounds in bulk?
Yes. Wrap the calls in multicall and they run concurrently instead of one after another — the usual pattern for a catalogue import where a hundred product photos arrive at once.
What is the difference between this and generate_transparent_image?
This one cuts out a picture you already have. generate_transparent_image creates the picture and cuts it out in a single call, which is what you want when there is no source photo to begin with.
8 credits. One call. Alpha channel intact.
The free tier gives you 30 credits a month — enough to test it on real photos.
Get an API key