Skip to content
Integration

Remove.bg integrations and automation

Describe what should happen in Remove.bg, and when, in plain words. Whenever builds the workflow and runs it on a schedule, on a webhook, or when another app sends an event.

Connection requirements, provider permissions and optional AI usage apply. Read the runtime limits.

Start for freeNo credit card requiredAI building has weekly usage limits.

Remove.bg on Whenever

About Remove.bg

remove_bg is an API that allows developers to automatically remove backgrounds from images using AI technology.

How Whenever connects

Through its API, using the credentials and permissions required by the provider.

Build it from your AI client

Connect Claude, Cursor or Codex to the Whenever MCP server and your coding agent can build and deploy the Remove.bg workflow. It runs on Whenever afterwards, on its schedule or webhook, with the chat closed.

Set up the Whenever MCP server

Plan your Remove.bg workflow

Remove.bg does one job in an automation: it takes a product shot, portrait or listing photo and returns a cutout. The whole API is essentially one call, POST /v1.0/removebg, authenticated with an X-Api-Key header, and it accepts either an uploaded file or an image URL. The real decisions sit in the request options: size, type (product, person, car, animal and others), format, bg_color, crop and crop_margin. Fix those once per catalogue so that every image in a batch comes out with the same framing and background instead of each run guessing.

Plan for a provider change before you build. Remove.bg has announced that, starting 1 December 2026, background removal moves to Leonardo.Ai, also part of Canva, and that the standalone remove.bg website will no longer be available from that date. Leonardo publishes a migration guide: a different endpoint, a bearer key, JSON-only requests, results returned as a download URL or base64, cost reported in the response body, and no ZIP output. Keep the background-removal call in a single step of the workflow so that switching the endpoint and credential later changes one place rather than the whole process.

Output format limits catch people out with large photos. PNG results are supported only up to 10 megapixels; for bigger transparent cutouts remove.bg points to WebP or its ZIP format, which contains a color.jpg and an alpha.png that must be composited afterwards. JPG has no transparency but suits white-background marketplace images made with bg_color. The size value auto keeps a 25-megapixel ceiling for backwards compatibility, while the 50MP size goes higher. Each response reports credits used in the X-Credits-Charged header, and GET /account returns the remaining balance.

Throughput depends on resolution: up to 500 images per minute at one megapixel, falling to 50 per minute at ten megapixels. Exceeding it returns HTTP 429 with a Retry-After header, and no credits are charged for that refusal, so a batch should wait as instructed rather than retry immediately. The service also needs a clear foreground subject. Route images it cannot separate to a person for review instead of publishing the original, and make sure the source images sit somewhere the hosted runtime can fetch, not on an office file server.

Remove.bg workflow examples

Authored starter briefs to configure with your accounts, not preconfigured workflows.

Nightly cutouts for new product photos

A batch job that processes only images without a cutout yet, records the credits used, and respects the per-minute limit.

Build this workflow

White-background JPGs for a marketplace listing

Uses bg_color and crop so the output already meets a plain-background listing rule, without needing transparency.

Build this workflow

Weekly credit balance warning

A read-only check of the account endpoint so a batch does not stall because credits ran out.

Build this workflow

Related apps for your workflows

All integrations

Remove.bg FAQs

What happens to the remove.bg API on 1 December 2026?

Remove.bg says background removal moves to Leonardo.Ai from that date and the standalone website will no longer be available. Leonardo’s migration guide documents the new endpoint, bearer-key authentication and JSON request format, so plan the switch before then.

How many images per minute can the remove.bg API handle?

Up to 500 images per minute for one-megapixel inputs. The limit is divided by input megapixels, so ten-megapixel images allow about 50 per minute. Higher limits are offered only to high-volume customers.

Why does a PNG result fail for a large photo?

PNG output is limited to 10 megapixels. For larger images that need transparency, request WebP or ZIP; if transparency is not needed, JPG supports up to 50 megapixels.

Are credits deducted when a request is rate limited?

No. A 429 response is not charged. Read the Retry-After header for the number of seconds to wait, and use the X-RateLimit-Remaining header to pace a batch.

Can the API return foreground position as well as the image?

Yes. Responses include the foreground’s top, left, width and height, as headers with an image result or as fields when you request data instead of a file. That helps when placing the cutout on a template.

Agents should build your automations, not be them

Describe your first workflow in plain words. One stays live for free, no credit card.

No credit card required