BiRefNet Background Remover — AI Image Background Removal & Cutout ✂️

Remove the background from any image automatically with BiRefNet, a state-of-the-art segmentation model. Get a clean, transparent PNG cutout in just a few seconds — plus an optional black-and-white mask for compositing. No GPU, no subscription, no monthly fees: you pay a tiny fixed price per image. A fast, affordable alternative to remove.bg, Photoroom, and Adobe's "Remove Background".

• ✂️ Transparent cutout — your subject on a clean alpha background (PNG or WebP).
• 🎭 Optional mask — the black-and-white segmentation mask, for compositing or downstream tools.
• 🪶 Edge refinement — smooth hair, fur, and fine detail out of the box.

Perfect for e-commerce product shots, marketplace listings, profile pictures, thumbnails, design assets, catalog automation, and n8n / Make / Zapier workflows and AI agents.

See it in action

Every output, from one run — the original image, the transparent cutout (PNG/WebP with a real alpha channel), and the optional black-and-white segmentation mask:

The cutout is a true transparent file — the checkerboard only visualizes the removed background and isn't part of the image. Turn on Also output the mask to additionally get the segmentation mask.

Why this Actor?

• ⚡ Fast — BiRefNet runs on dedicated GPUs and returns a cutout in a few seconds.
• 💸 Cheap — from $0.007 per image (as low as $7 per 1,000) — ~2× under Photoroom and 5–20× under remove.bg. Pay only for successful results; failed runs are never charged.
• 🎯 Accurate — BiRefNet is a top-performing dichotomous image segmentation model, great on hair, fur, and intricate edges.
• 🪟 True transparency — PNG/WebP output with a real alpha channel, ready to drop onto any background.
• 🎭 Mask on demand — flip one switch to also get the raw segmentation mask.
• 🔌 Automation-ready — call it from the Apify API, n8n, Make, Zapier, LangChain, or any AI agent via MCP.

How it compares

	This Actor (BiRefNet)	remove.bg / Photoroom
Pricing model	Pay per image (from $0.007)	Monthly subscription / credits
Commitment	None — pay only for what you run	Recurring plan, credits expire
Failed runs	Never charged	Often consume credits
Transparent PNG	Yes	Yes (often paywalled at full res)
Segmentation mask	Yes, optional	Rarely exposed
API & automation	Native Apify API, n8n, Make, Zapier, MCP	Varies / limited
Watermark / resolution cap	None	Common on lower tiers

Great when you want background removal on demand without a subscription — ideal for occasional use, automated pipelines, and pay-as-you-go scaling.

How it works

1. Provide a public image URL.
2. Choose your output format (PNG or WebP) and, optionally, turn on Also output the mask.
3. The Actor removes the background and stores the cutout (and mask) in the run's dataset and key-value store.
4. Download the file(s) from the output, or pipe the URL into the next step of your workflow.

Input example

{
    "imageUrl": "https://cdn.doggi-dev.net/ofai/plan_plan-cf945bca478a4ad5ac3e48a93130da47/output.jpg",
    "outputFormat": "png",
    "outputMask": true,
    "refineForeground": true
}

Field	Type	Default	Description
imageUrl	string	— (required)	Public URL of the image to process (JPG, PNG, WebP).
outputFormat	string	png	Cutout file format — png or webp (both keep transparency).
outputMask	boolean	false	Also return the black-and-white segmentation mask.
refineForeground	boolean	true	Clean up edges for smoother hair, fur, and fine detail.

Output example

{
    "imageUrl": "https://api.apify.com/v2/key-value-stores/.../records/cutout.png?signature=...",
    "maskUrl": "https://api.apify.com/v2/key-value-stores/.../records/mask.png?signature=...",
    "sourceImageUrl": "https://cdn.doggi-dev.net/ofai/plan_plan-cf945bca478a4ad5ac3e48a93130da47/output.jpg",
    "outputFormat": "png",
    "outputMask": true,
    "refineForeground": true,
    "width": 1024,
    "height": 1024,
    "requestId": "req-...",
    "contentType": "image/png",
    "model": "ZhengPeng7/BiRefNet"
}

The cutout is also stored in the run's key-value store under the key cutout.png (or cutout.webp), and the mask — when requested — under mask.png (or mask.webp).

Pricing

You are charged per processed image at a price that drops with your Apify plan. The price is the same whether or not you also request the mask.

Apify plan	Price per image	Per 1,000 images
Free	$0.0100	$10.00
Bronze	$0.0090	$9.00
Silver	$0.0080	$8.00
Gold / Platinum / Diamond	$0.0070	$7.00

That's still the cheapest pay-as-you-go background-removal API around — roughly 2× cheaper than Photoroom's API (~$0.02/image) and 5–20× cheaper than remove.bg ($0.05–0.20/image), with no monthly subscription and no expiring credits.

Failed runs are never charged — you only pay for cutouts you actually receive. (Apify also applies its standard tiny platform fees for the Actor start and each dataset record.)

Tips for great results

• Use a clear subject — BiRefNet excels when the foreground stands out from the background.
• Keep resolution reasonable — very large images take a little longer; downscale first if you don't need full size.
• Output PNG for maximum compatibility, or WebP for smaller files — both preserve transparency.
• Turn on the mask when you want to composite, soften edges, or feed the selection into another tool.
• Leave edge refinement on for portraits and anything with hair or fur.

🎨 Need images to cut out? — FLUX.2 Klein Image Generator

No source image yet? Generate one. Our companion Actor, FLUX.2 Klein Image Generator, creates high-quality images from a text prompt (or edits an existing photo) in seconds — then pipe the imageUrl straight into this Actor to get a clean cutout.

The complete pipeline:

FLUX.2 Klein → image
  → BiRefNet Background Remover (this Actor) → transparent cutout
  → composite / list product / post to social

👉 Try FLUX.2 Klein Image Generator →

Use it from the API

curl -X POST "https://api.apify.com/v2/acts/danitn11~birefnet-background-remover/runs?token=YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{ "imageUrl": "https://example.com/photo.jpg", "outputFormat": "png", "outputMask": true }'

Works the same from the Apify n8n node, Make, Zapier, LangChain, or the Apify MCP server for AI agents.

For the full request/response shape (run-sync, async, polling, downloading the cutout), see the OpenAPI spec at ./openapi.yaml — import it into Postman, Insomnia, or any OpenAPI client.

Templates & integrations

Drop this Actor into a no-code workflow to automate background removal end to end. In each tool, search for the Apify connector, authenticate with your Apify API token, and select danitn11/birefnet-background-remover with the action Run Actor (or Run Actor and get dataset items to receive the cutout URL back).

• n8n — add the Apify node → Run Actor, map imageUrl from a previous step (e.g. a new row in a Sheet or an uploaded product photo), then push the resulting imageUrl to your storage or publishing node.
• Make.com — use the Apify › Run an Actor module, then a Watch / Get dataset items module to read back imageUrl. Chain into Shopify, Google Drive, or an image uploader.
• Zapier — trigger (new file, form submission, etc.) → Apify: Run Actor → action (update a product listing, save to Drive, send a Slack message).

Common pattern — automated product-photo pipeline:

New product photo (Sheet / form / webhook)
  → Run this Actor (imageUrl)
  → Get cutout imageUrl
  → Place on white/branded background / upload to store

Use with AI agents (MCP server)

This Actor works as a tool for any MCP-compatible AI agent (Claude, Cursor, VS Code Copilot, custom agents) through Apify's hosted MCP server. Your agent can remove backgrounds as part of a larger task — "cut out this product and place it on white" — with billing through your Apify account.

Server URL (with this Actor preselected as a tool):

https://mcp.apify.com?tools=danitn11/birefnet-background-remover

Authenticate with OAuth (you'll be redirected on first connect) or an Authorization: Bearer <APIFY_TOKEN> header.

Claude Code

$claude mcp add --transport http apify "https://mcp.apify.com?tools=danitn11/birefnet-background-remover" -H "Authorization: Bearer <APIFY_TOKEN>"

Claude Desktop / claude.ai — add a custom connector with the server URL above (OAuth flow handles auth).

Cursor / VS Code — add to .cursor/mcp.json (or "MCP: Open User Configuration" in VS Code):

{
    "mcpServers": {
        "apify": {
            "url": "https://mcp.apify.com?tools=danitn11/birefnet-background-remover",
            "headers": { "Authorization": "Bearer <APIFY_TOKEN>" }
        }
    }
}

Local stdio (npx)

{
    "mcpServers": {
        "apify": {
            "command": "npx",
            "args": ["-y", "@apify/actors-mcp-server", "--tools", "danitn11/birefnet-background-remover"],
            "env": { "APIFY_TOKEN": "<APIFY_TOKEN>" }
        }
    }
}

Then just ask your agent: "Remove the background from this image and give me a transparent PNG." The agent calls the Actor, waits for the result, and gets back the cutout URL from the output schema.

FAQ

How long does background removal take? Typically just a few seconds — BiRefNet runs on dedicated GPUs.

What image formats are supported? Input: JPG, PNG, and WebP via a publicly accessible URL. Output: PNG or WebP — both with a transparent background.

Do I get a transparent background? Yes. The cutout is a real alpha-channel PNG (or WebP), ready to drop onto any background.

Can I get the mask too? Yes — turn on Also output the mask and the Actor returns the black-and-white segmentation mask as a second file.

Is there a watermark or resolution cap? No. The output is clean and full-resolution, ready to publish.

What model is used? BiRefNet (ZhengPeng7/BiRefNet) — a state-of-the-art bilateral reference network for high-accuracy image segmentation.