canonical: https://jentic.com/apis/objectcut.com/objectcut

# ObjectCut API

ObjectCut is an image background and foreground removal API distributed through the RapidAPI marketplace. The service accepts either a URL or an uploaded image and returns a processed image with the chosen layer removed, using AI segmentation to handle hair, fur, and complex edges. It suits e-commerce product image pipelines, creative tools, and document processing where consistent cutouts are needed at scale.

## For AI agents

Remove backgrounds or foregrounds from images via URL or upload using AI segmentation, returning the processed image.

## Scope

Does not run object detection, image generation, upscaling, or face recognition - use for AI background and foreground removal only.

## Capabilities

- Remove the background from an image referenced by URL and return the cutout
- Remove the background from an uploaded image submitted as multipart form data
- Process product photos at scale to produce consistent transparent backgrounds
- Strip backgrounds from user-submitted photos before storing them in a CMS
- Handle complex edges such as hair and fur using the AI segmentation model

## Use cases

### E-commerce product image cleanup

Standardise product imagery across an online store by sending each photo URL to POST `/api/v1/remove-background` and storing the returned cutout. ObjectCut applies AI segmentation, which handles glossy surfaces and soft edges better than a fixed threshold mask, so a catalogue manager can run a batch over thousands of SKUs without manual retouching. The pipeline cuts hours of designer time per product launch.

Example prompt: For each URL in a product image list, call POST `/api/v1/remove-background` and save the returned cutout to the catalogue store

### User-generated content moderation pipelines

Strip backgrounds from user-uploaded photos before they are stored or displayed by sending the upload through POST `/api/v1/remove-background/upload.` The endpoint accepts multipart form data, so a moderation worker can handle images directly from a form post without needing a public URL. The cleaner output simplifies downstream face detection and classification.

Example prompt: POST a user-submitted image to `/api/v1/remove-background/upload` and store the cutout for downstream moderation review

### Creative tool integration

Add a one-click 'remove background' feature to a design or content tool by wiring the user's selected image through ObjectCut. The API returns the processed image directly, which lets the tool drop it back onto the canvas with transparency preserved. Because both URL and upload variants exist, the integration handles assets from cloud libraries and local pickers.

Example prompt: When a user clicks 'remove background', POST the active image to `/api/v1/remove-background/upload` and replace the canvas image with the response

### AI agent integration via Jentic

A creative agent searches Jentic for background removal, loads the POST `/api/v1/remove-background` schema, and processes incoming product images for a daily catalogue update. The agent references a list of URLs, calls the endpoint per image, and writes the output to a designated bucket. Jentic supplies the validated schema so the agent can build the pipeline without reading the RapidAPI listing manually.

Example prompt: Use Jentic to search 'remove image background', load POST `/api/v1/remove-background`, and execute it for each URL in the daily product image queue

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/api/v1/remove-background` | Remove background from an image referenced by URL |
| POST | `/api/v1/remove-background/upload` | Remove background from an uploaded image (multipart) |

## Key resources

- **Background Removal** — AI background and foreground removal via URL or uploaded image

## Why Jentic

- **Setup:** Wiring the ObjectCut API by hand means holding a RapidAPI key, adding it to the x-rapidapi-key header, pointing at the objectcut.p.rapidapi.com host, and coding your own retry handling. Through Jentic you install once, import the ObjectCut API from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** ObjectCut exposes only background and foreground removal, so scope it by operation: limit the agent to the removal operations it needs, such as the URL-based removal or the upload variant, and leave the other out unless you add it. You choose which operations it may call, so nothing beyond image cutout runs.
- **Credential handling:** Your RapidAPI key is stored once, encrypted, by your own Jentic One instance and injected into the x-rapidapi-key header at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'remove an image background', and Jentic returns the matching ObjectCut operation with its input schema so the agent calls the right variant without reading the RapidAPI page.

## Related APIs

- **remove.bg API** — The most established AI background removal API - broader plan tiers and direct (non-RapidAPI) distribution
- **PhotoRoom API** — AI image editing focused on product photography - adds shadow generation and scene placement on top of cutouts
- **Cloudinary Upload API** — Image storage, transformation, and CDN - pair with ObjectCut to host and serve the cutouts

## FAQ

### What authentication does the ObjectCut API use?

ObjectCut is distributed through RapidAPI and authenticates with the x-rapidapi-key header on every call to `/api/v1/remove-background` and `/api/v1/remove-background/upload.` Through Jentic the RapidAPI key is held in the vault (your Jentic One instance) and injected at execution time so it never enters the agent's prompt context.

### Can I send an image URL or do I need to upload the file?

Both. POST `/api/v1/remove-background` accepts an image URL in the body, while POST `/api/v1/remove-background/upload` accepts the image as multipart form data. Pick the URL variant when the image is already hosted publicly and the upload variant when you have raw bytes from a form or local file.

### Does ObjectCut handle complex edges like hair?

Yes. The AI segmentation model is designed to handle hair, fur, and similarly soft boundaries, which is why it ships behind a single endpoint rather than a tunable threshold. Results are returned as the processed image so the agent can store or display it directly.

### What are the rate limits for the ObjectCut API?

The OpenAPI spec does not publish explicit rate limits. ObjectCut throttles per RapidAPI plan tier - check your RapidAPI subscription for monthly request and concurrency limits. Through Jentic, the agent loop can pace calls so a batch run does not breach the plan.

### How do I remove a product photo background through Jentic?

Install the SDK with pip install jentic, search 'remove image background', load POST `/api/v1/remove-background`, and execute it with the public image URL. Jentic returns the processed image bytes so the agent can write the cutout to its catalogue store.

### Can I use ObjectCut for foreground removal as well?

The API description covers both background and foreground removal. The published endpoints are framed as remove-background; if you need a different layer mode, check the RapidAPI listing for parameter options or contact ObjectCut. The Jentic schema reflects whichever fields the spec exposes.

### Can I limit what my agent is allowed to do with the ObjectCut API?

Yes. Because you run Jentic One yourself, your own rules decide which ObjectCut operations the agent may call and which credential it uses. ObjectCut exposes only two operations, the URL-based removal at POST `/api/v1/remove-background` and the upload variant at POST `/api/v1/remove-background/upload`, so you can grant the agent just one of them and leave the other out. Scoped this way, nothing beyond image background and foreground removal ever runs, and the RapidAPI key stays under your control.