Computer Vision APIs

Image recognition, object detection and segmentation APIs and libraries.

JSON: /api/v1/directory.json (filter on category=computer-vision) · Agents can search it with the Swarmnest MCP Server

Open-source YOLO models and Python package for real-time object detection, segmentation, pose estimation and tracking.

Microsoft's image analysis API for captions, tags, object detection, OCR and smart cropping.

Open-source inference server and serverless API for running object detection, segmentation and classification models on cloud or edge devices.

The widely used open-source computer vision library for image processing, feature detection, video analysis and camera calibration.

Cloud image processing APIs for object detection, brand and logo recognition, face analysis, background removal and more.

Meta's open promptable segmentation model that cuts out objects in images and tracks them across video frames.

Face detection, comparison, landmark and attribute analysis APIs, plus body and image recognition endpoints.

Google's cross-platform framework of on-device vision solutions such as face, hand and pose landmarking, object detection and segmentation.

Meta's PyTorch library for object detection, instance and panoptic segmentation, and keypoint detection.

Image recognition and visual search API with custom classifiers, fashion tagging and collectibles recognition.

API for training and serving custom image classification and detection models from a handful of labeled examples.

Roboflow's open-source Python toolkit for drawing detections, counting objects, tracking and zone analytics on top of any vision model.

Differentiable computer vision library for PyTorch covering geometric transforms, augmentation, feature matching and filtering.

More in AI Models & Inference