# Background Remover - Core.Today AI API > The most-used background remover on Replicate (27M+ runs). Removes backgrounds with soft alpha or hard segmentation, supports reverse mode (remove foreground), custom background types, and transparent PNG output — all at a very low price. - **Provider**: 851 Labs - **Model ID**: 851-labs/background-remover - **Category**: Image Generation - **Credits**: 1 per image - **Speed**: Fast - **Quality**: High ## Features - Most-used background remover on Replicate - Soft alpha matte or hard segmentation (threshold) - Reverse mode — remove the foreground instead - Custom backgrounds: transparent, white, green, blur, overlay - Extremely low cost (2 credits per image) ## Use Cases - Product photos for e-commerce - Profile picture cutouts - Bulk catalog image processing - Sticker and thumbnail creation - Green-screen compositing prep ## API Endpoint Base URL: https://api.core.today/v1 Create Prediction: POST /predictions Get Status: GET /predictions/{job_id} ## Authentication Header: X-API-Key: YOUR_API_KEY ## Input Parameters ### Required - **image**: string - Input image to remove the background from ### Optional - **threshold**: number (default: 0) - Hard segmentation threshold (0.0-1.0). 0 uses soft alpha matte - **reverse**: boolean (default: false) - Remove the foreground instead of the background - **background_type**: string (default: rgba) - 'rgba' (transparent), 'white', 'green', 'blur', 'overlay', 'map', an [R,G,B] array, or an image URL - **format**: string (default: png) - Output format (png for transparency, jpg) ## Examples ### Transparent Product Cutout Remove the background and get a transparent PNG ```json { "model": "851-labs/background-remover", "input": { "image": "https://example.com/product.jpg", "format": "png", "background_type": "rgba" } } ``` ### White Background for Marketplace Replace the background with clean white ```json { "model": "851-labs/background-remover", "input": { "image": "https://example.com/product.jpg", "background_type": "white" } } ``` ## Response Format ```json { "job_id": "abc123", "status": "pending | processing | completed | failed", "result": "URL or data (when completed)" } ``` ## Usage Flow 1. POST /predictions with model and input -> receive job_id 2. GET /predictions/{job_id} -> poll until status is completed or failed 3. Result contains output URL(s) ## Tips - Keep threshold at 0 (soft alpha) for hair and fine edges; raise it for crisp hard cutouts - Use format: png with background_type: rgba for transparency - background_type: blur gives an instant portrait-mode effect - At 2 credits per image, it's ideal for bulk catalog processing - For the highest edge fidelity on difficult subjects, compare with BiRefNet ## Documentation https://replicate.com/851-labs/background-remover