Detect and identify objects from an input image. It locates bounding boxes, classify objects, and return structured metadata describing each detected entity.

• Accurate bounding boxes and segmentation masks for each object
• Support for a wide range of industries, construction, retail, healthcare, biology, and more
• Computer GUI detection

Real time object detection of an image

Bounding boxes mapped to the image

JSON output

object contains the extracted information defined in the schema. precontext contains the raw metadata such as bounding boxes and confidence scores.

Run object detection task with raw output

Running object detection as a single task with <task>object_detection</task> in the system message makes it cheaper and faster with a fixed structured output that's pre-defined.

Learn more about running a task.

JSON output