Merchant details, line items, tax, and totals — extracted as typed, auditable JSON from photos, scans, or PDFs. Every value carries a source citation and confidence score, so nothing reaches expense approval unreviewed.
Trusted by enterprises, governments, and teams building document workflows at scale
USE CASES
GOVERNED EXTRACTION
LLMs can reason over a receipt — but expense workflows need deterministic, auditable output grounded in the source file, not generated answers that vary between runs.
LLM-only prompting
Nutrient Data Extraction API
Output shape
LLM-only prompting
Generated answers that can change between runs.
Nutrient Data Extraction API
Predictable structured output — typed and tied to the source receipt.
Routing signal
LLM-only prompting
No signal for which values to trust.
Nutrient Data Extraction API
Confidence signals route uncertain values to human review before expense approval.
Traceability
LLM-only prompting
No way to point back at the page.
Nutrient Data Extraction API
Coordinates and page references anchor every value to its source location.
Line items
LLM-only prompting
Tables flattened into unstructured text.
Nutrient Data Extraction API
Layout-aware structure preserves line items and totals with their layout context.
Review step
LLM-only prompting
Values reach downstream systems unchecked.
Nutrient Data Extraction API
Human review and validation before expense or accounting systems.
Audit
LLM-only prompting
Nothing to show an auditor.
Nutrient Data Extraction API
Source context and page detail support traceable, audit-ready expense workflows.
Try it live
Switch processing modes and inspect live output from a sample invoice as rendered Markdown, raw Markdown, or spatial JSON.
HOW IT WORKS
Parse
Turn receipt photos, scans, and PDFs into document structure.
Extract
Identify merchant details, line items, tax, and totals from the receipt.
Map
Define the fields your workflow needs using the schema generator in Studio, or write a JSON Schema directly. Get back validated, typed output.
Structure
Return typed JSON for systems and validation, or Markdown for search and AI workflows.
Process
Send structured data into expense review queues or accounting systems.
OUTPUT FORMATS
Confidence scores, coordinates, and page context included.
Choose output: "json" or Markdown per request.
Spatial JSON
For extraction · validation · review
{ "type": "keyValueRegion", "id": "kv_j1k2l3", "bounds": { "x": 40, "y": 60, "width": 260, "height": 96 }, "confidence": 0.98, "page": { "pageIndex": 0, "pageNumber": 1 }, "pairs": [ { "key": { "entityType": "QUESTION", "value": "Merchant", "bounds": { "x": 40, "y": 60, "width": 80, "height": 22 }, "confidence": 0.99 }, "value": { "entityType": "ANSWER", "value": "Blue Bottle Coffee", "bounds": { "x": 128, "y": 60, "width": 172, "height": 22 }, "confidence": 0.99 }, "relationshipConfidence": 0.97 }, { "key": { "entityType": "QUESTION", "value": "Date", "bounds": { "x": 40, "y": 94, "width": 80, "height": 22 }, "confidence": 0.98 }, "value": { "entityType": "ANSWER", "value": "2024-05-02", "bounds": { "x": 128, "y": 94, "width": 100, "height": 22 }, "confidence": 0.98 }, "relationshipConfidence": 0.96 }, { "key": { "entityType": "QUESTION", "value": "Total", "bounds": { "x": 40, "y": 128, "width": 80, "height": 22 }, "confidence": 0.99 }, "value": { "entityType": "ANSWER", "value": "$14.75", "bounds": { "x": 128, "y": 128, "width": 60, "height": 22 }, "confidence": 0.99 }, "relationshipConfidence": 0.98 } ]}Markdown
For RAG · search · knowledge bases
# Receipt
**Merchant** Blue Bottle Coffee**Date** 2024-05-02
| Item | Qty | Price || --- | --- | --- || Cappuccino | 1 | 5.25 || Croissant | 1 | 4.50 |
**Subtotal** 9.75**Tax** 0.75**Total** 14.75ACCURACY
Receipt-specific accuracy benchmarks are still being validated against public gold-annotated receipt datasets. In the meantime, the general Data Extraction API benchmark — reading order, table structure, and heading hierarchy, tested on a 200-document corpus with every release — is the current accuracy proof.
Regional processing options
Choose supported processing regions for enterprise deployments.
SOC 2 Type 2 audited
Audited annually. Reports available under NDA for enterprise customers.
Trust and compliance
TLS encryption by default
All API communication is encrypted. Unencrypted requests are rejected.
Configurable data retention
Encrypted transport and plan-level retention controls for expense document workflows.
Yes. The API accepts photographed receipts alongside scans and PDFs, running OCR-based extraction to identify merchant details, line items, and totals regardless of capture method.
Data Extraction API processes images (including phone photos), PDFs, and Word, Excel, and PowerPoint files. It handles crumpled, faded, or low-quality receipts without requiring a separate OCR pipeline.
No. Nutrient Data Extraction API is an extraction layer, not an expense management suite. It turns receipts into structured data so that data can be reviewed, validated, and routed into the expense or accounting system your team already uses.
Every extracted field includes a match label, confidence score, page reference, and bounding box, so uncertain fields can be flagged for human review and traced back to the source receipt before entering expense approval.
Use the schema generator in Studio — upload example receipts and describe the fields needed. It generates a JSON Schema for the `/extract` endpoint. Fields like merchant, line items, and totals can also be defined manually.
Use agentic mode for degraded, faded, or low-quality receipt photos where understand mode produces insufficient results. Agentic mode adds a vision language model (VLM) on top of the understand pipeline. It costs 18 credits per page.