Field Extraction

LlamaExtract

Define a custom schema and extract structured fields with confidence information and source citations.

At a glance

Input
Document files; verify the service format list
Output
JSON
Provenance
Field citations; exact granularity depends on mode
Scanned pages
Verify the parsing mode
Deployment
Cloud API
Availability
Commercial
Costs to plan for
Usage-based

Limitations to check

Confidence is not a guarantee of correctness. Check citation detail, supported formats, and scan quality in your chosen extraction mode.

Build a meaningful sample

Include your hardest pages: low-quality scans, missing fields, dense tables, and evidence split across pages. Validate output correctness separately from citation accuracy.