Published methodology. Named competitors.
The benchmark suite, the document corpus, and the methodology are public, so procurement verifies the numbers instead of trusting them.
Large filings, dense earnings packets, broker decks, footnoted contracts — find the needle in the haystack, with citations back to the source. Accurate, auditable, and ready to deploy wherever and whenever you need it.








Methodology and corpus available at benchmarks. Marker, Surya, and Chandra are open source — and Chandra is the model running inside the Datalab API.
Multi-column, footnoted, merged-cell multi-page tables
Try in playground →D · 02 Earnings reportsSlides, tables, transcripts in one packet
Try in playground →D · 03 Broker researchCharts extracted as assets, citations, multi-column
Try in playground →D · 04 ProspectusesLong-form, regulatory boilerplate, structured fields
Try in playground →D · 05 Contracts & ISDAsClauses, schedules, definitional sections
Try in playground →D · 06 Statements & filingsMulti-period merged-cell tables, mixed templates
Try in playground →The benchmark suite, the document corpus, and the methodology are public, so procurement verifies the numbers instead of trusting them.
Multi-column 10-K tables, footnoted regions, multi-period statements, and ISDA definitional sections are checked on every model release.
Schema-defined extraction emits typed JSON with a page coordinate per field, so risk and compliance trace each number back instantly.
Start with an API key — nothing to host or operate.
Sign up →Run in-region, with no egress to US infrastructure.
Sign up →Runs inside your own AWS, GCP, or Azure account.
Talk to sales →Fully offline, the same model weights, dedicated support.
Talk to sales →Free tier with up to $20 in credits per month — no card required.