Send a PDF, image, or text plus a schema. Get clean, typed JSON back with confidence scores. One API call. That simple.
// One API call to extract structured data const result = await fetch("https://api.ramlabs.dev/v1/extract", { method: "POST", headers: { "Authorization": `Bearer ${API_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ document: invoicePdfBase64, documentType: "pdf", schema: "invoice", }), }); // Get typed JSON with confidence scores const { data, confidence } = await result.json(); // data.vendor_name = "Acme Corp" (confidence: 0.98) // data.total_amount = 1500.00 (confidence: 0.99)
PDF, images (JPEG, PNG, WebP), and plain text. Send base64 or raw text, we handle the rest.
Define exactly what you want. Use pre-built templates (invoice, receipt, resume, contract) or bring your own schema.
Every extracted field includes a 0-1 confidence score so you know when to trust the output and when to flag for review.
Deployed on Cloudflare Workers for sub-second cold starts globally. Most extractions complete in 1-3 seconds.
Clean REST API, clear error messages, Python and Node.js examples. Get integrated in minutes, not days.
Pay only for what you use. Free tier to start, transparent metered billing via Lemon Squeezy. No surprises.
From document to structured data in seconds.
Use a pre-built template (invoice, receipt, resume, contract) or define any custom JSON schema with the fields you need.
POST a PDF, image, or text to the API. Base64-encode files or send raw text. One endpoint handles everything.
Receive typed JSON matching your schema with per-field confidence scores. Auto-process high-confidence results, flag low ones for review.
Compare the developer experience.
| ScoutExtract | AWS Textract | Google Document AI | |
|---|---|---|---|
| Integration time | Minutes | Hours–Days | Hours–Days |
| Output format | Typed JSON matching your schema | Raw text blocks + bounding boxes | Entities + key-value pairs |
| New document types | Zero-shot (just change schema) | Custom adapters needed | Requires training data |
| Confidence scores | Per-field, 0–1 | Per-block only | Per-entity |
| Free tier | 100/month, no card | 1,000/month (12 months) | Trial credits |
Start free. Scale as you grow. No hidden fees.
Get your API key and extract data in under 60 seconds.
# Step 1: Get your free API key curl -X POST https://api.ramlabs.dev/v1/auth/register \ -H "Content-Type: application/json" \ -d '{"email": "you@company.com"}' # Step 2: Extract data from any document curl -X POST https://api.ramlabs.dev/v1/extract \ -H "Authorization: Bearer rex_your_key" \ -H "Content-Type: application/json" \ -d '{"document": "Invoice #1234\nDate: 2026-01-15\nVendor: Acme Corp\nTotal: $1,500.00", "schema": "invoice"}' # Returns: # {"data": {"invoice_number": "1234", "vendor_name": "Acme Corp", "total_amount": 1500.00, ...}, # "confidence": {"invoice_number": 0.98, "vendor_name": 0.99, "total_amount": 0.99}}
100 free extractions per month. No credit card required.
Get Your Free API Key