Skip to main content
Our cloud-hosted API documentation can be found here. With caveats and exceptions detailed below, the container image shares the same API.
The on-prem container currently uses /api/v1/marker. The new dedicated endpoints (/convert, /extract, /segment) will be available in a future container release.

Supported endpoints

The container currently supports:
  • /api/v1/marker documented here. This uses both the Marker and Chandra models.
  • /api/v1/ocr documented here.
  • /api/v1/usage documented here — provides usage analytics and performance metrics for your on-prem deployment.

Authentication

API authentication is not supported in the container. We assume customers will be running our image on their own infrastructure in private networks. You may send the X-API-Key header detailed here, but it will be ignored and any value works.

PDFs and images are supported, document conversion not yet supported

Datalab’s API supports many file types. The container currently supports PDFs and image file types. Other file types are not yet supported, but will be supported in an upcoming release.

Feature Parity

FeatureCloud APIOn-Premises
Document conversion (/marker)YesYes
OCR (/ocr)YesYes
Output formats (markdown, html, json, chunks)YesYes
Parse quality scoringYesYes
Chart understandingYesYes (Chandra containers only)
Page range selectionYesYes
Block IDsYesYes
Token-efficient markdownYesYes
Form filling (/fill)YesNo
Create document (/create-document)YesNo
ThumbnailsYesNo
Accurate modeYesNo
Fast modeYesNo
Link extractionYesNo
CheckpointsYesNo
File URL downloadYesNo
Structured extractionYesNo
Document segmentationYesNo
On-premises containers do not require API key authentication. Implement access control at the network or reverse proxy level.

Next Steps

Usage Analytics

Monitor request volumes, performance metrics, and system status.

Running the Container

Get the on-prem container up and running in minutes.

Cloud API Reference

Full REST API reference that the on-prem container mirrors.

On-Prem Overview

Compare open-source and paid on-prem options.