API Reference

Every endpoint, grouped by what it does. Each page explains the endpoint in plain language first, then lists its parameters, responses and examples.

Base URLhttps://api.anchorgrid.ai

AuthenticationX-API-Key header on every request. Details

ResultsAnalyses run as jobs. Check your results

Documents

Start every integration by uploading a PDF.

Upload a documentSend a drawing set or specification PDF. You get back a document_id that every analysis uses.POST /v1/documents

Find doors, rooms, fixtures and wall materials on drawing pages.

Detect doorsFind the doors on the pages of an architectural drawing set.POST /v1/drawings/detection/doorsElement detection, per sheet
Detect toiletsFind toilets and plumbing fixtures on architectural floor plans, with a confidence score for each.POST /v1/drawings/detection/toiletsElement detection, per sheet
Detect roomsFind rooms on floor plans, with outlines, areas and, when available, room numbers and names.POST /v1/drawings/detection/roomsElement detection, per sheet
Detect wall materialsDetect rooms, derive their wall segments and resolve each wall’s partition material in one job.POST /v1/drawings/detection/wall-materialsElement detection, per sheet

Index a drawing set’s sheets, elevations and schedules, read a specification’s structure and extract full sections.

Classify drawingsIndex every page of a drawing set: sheet number, title, drawing type, CSI division, scope and floor.POST /v1/drawings/classifyDocument indexing, per page read
Detect elevationsFind interior elevations on architectural drawing pages.POST /v1/drawings/detection/elevationDocument indexing, per page read
Extract schedulesPull tabular schedules out of architectural PDF drawings as structured data.POST /v1/drawings/schedulesDocument indexing, per page scanned
Read a spec’s table of contentsParse the table-of-contents structure of a construction specification.POST /v1/specs/parse/documentDocument indexing, per page read (up to 40)
Extract spec sectionsPull the full content of specification sections, with optional structured output.POST /v1/specs/content-extractDocument indexing, per page of the sections extracted

Every analysis runs as a job. Check it here.

Check your resultsSee a job’s status and, once it’s complete, its results.GET /v1/jobs/{job_id}