{
"document_type": {
"value": "invoice",
"quote": "Invoice INV/2023/03/0008",
"confidence": 0.9
},
"vendor": {
"name": {
"value": "Global Wholesaler",
"quote": "Global Wholesaler",
"confidence": 0.95
},
"address": {
"value": "Azure Interior 4557 De Silva St Fremont CA 94538 United States",
"quote": "Azure Interior 4557 De Silva St Fremont CA 94538 United States",
"confidence": 0.95
},
"vat_id": {
"value": null,
"quote": null,
"confidence": null
},
"email": {
"value": "[email protected]",
"quote": "[email protected]",
"confidence": 0.95
},
"phone": {
"value": "(870)-931-0505",
"quote": "(870)-931-0505",
"confidence": 0.95
},
"iban": {
"value": "US1234567890",
"quote": "US1234567890",
"confidence": 0.95
}
},
"customer": {
"name": {
"value": "YourCompany",
"quote": "YourCompany, Mitchell Admin",
"confidence": 0.95
},
"address": {
"value": "215 Vine St Scranton PA 18503 United States",
"quote": "215 Vine St Scranton PA 18503 United States",
"confidence": 0.95
},
"vat_id": {
"value": null,
"quote": null,
"confidence": null
}
},
"invoice_number": {
"value": "INV/2023/03/0008",
"quote": "Invoice INV/2023/03/0008",
"confidence": 0.95
},
"order_number": {
"value": "CUSTREF123",
"quote": "Reference:CUSTREF123",
"confidence": 0.95
},
"issue_date": {
"value": "2023-03-20",
"quote": "03/20/2023",
"confidence": 0.9
},
"due_date": {
"value": "2023-04-04",
"quote": "04/04/2023",
"confidence": 0.9
},
"currency": {
"value": "USD",
"quote": "$ 112.00",
"confidence": 0.9
},
"payment_terms": {
"value": "15 Days",
"quote": "Payment terms: 15 Days",
"confidence": 0.95
},
"totals": {
"subtotal": {
"value": 262.9,
"quote": "Subtotal $ 262.90",
"confidence": 0.98
},
"vat_total": {
"value": 16.94,
"quote": "Tax 15% on $ 112.90 $ 16.94",
"confidence": 0.98
},
"total": {
"value": 279.84,
"quote": "Total $ 279.84",
"confidence": 0.98
},
"amount_due": {
"value": null,
"quote": null,
"confidence": null
}
},
"vat_breakdown": [
{
"rate": 15,
"base": 112.9,
"amount": 16.94,
"quote": "$ 16.94",
"confidence": 0.85
}
],
"line_items": [
{
"description": "Beeswax XL",
"quantity": 1,
"unit_price": 42,
"amount": 42,
"vat_rate": 15,
"quote": "[17589684] Beeswax XL Acme beeswax 1.00 kg 42.00 0.00 15.00% $ 42.00",
"confidence": 0.85
},
{
"description": "Office Chair",
"quantity": 1,
"unit_price": 70,
"amount": 70,
"vat_rate": 15,
"quote": "[FURN_7777] Office Chair 1.00 Units 70.00 0.00 15.00% $ 70.00",
"confidence": 0.85
},
{
"description": "Olive Oil",
"quantity": 1,
"unit_price": 1,
"amount": 0.9,
"vat_rate": 15,
"quote": "*987123* Olive Oil 1.00 L 1.00 10.00 15.00% $ 0.90",
"confidence": 0.85
},
{
"description": "Luxury Truffles",
"quantity": 15,
"unit_price": 10,
"amount": 150,
"vat_rate": null,
"quote": "[LUX_TRF] Luxury Truffles 15.00 g 10.00 0.00 $ 150.00",
"confidence": 0.85
}
],
"checks": {
"subtotal_plus_vat_equals_total": true,
"line_items_sum_equals_subtotal_or_total": true,
"vat_breakdown_sum_equals_vat_total": true,
"due_date_not_before_issue_date": true
},
"overall_confidence": 0.94,
"missing": [
"vendor_vat_id",
"customer_vat_id",
"amount_due"
],
"pages": 1,
"billed_usd": 0.0075,
"input": "pdf",
"text_chars": 1036,
"model": "@cf/mistralai/mistral-small-3.1-24b-instruct",
"timing_ms": {
"pdf_text_ms": 826,
"extract_ms": 14828,
"total": 15654
},
"confidence_method": "Per field: 0.6 if the quote is found verbatim in the document text (+0.3 if the value matches the quote; 0.35 base if the quote is not verbatim), then +0.08/-0.15 from the arithmetic checks for totals. Values with confidence < 0.6 should be reviewed.",
"limits": "LLM extraction can misread layouts; check important values (quotes make that quick). Scanned PDFs need image input. Documents are not stored.",
"sources": [
{
"name": "Cloudflare Workers AI: toMarkdown (PDF text layer), Mistral Small 3.1 24B (OCR of images + field extraction; fallback Llama 3.3 70B / Llama 4 Scout / Gemma 3 12B)",
"url": "https://developers.cloudflare.com/workers-ai/",
"note": "Documents are processed in memory and not stored or logged. No third-party LLM API."
}
]
}
curl --location --request GET 'https://zylalabs.com/api/14523/invoice+and+text+to+json+extraction+api/37076/invoice+to+json?url=https://raw.githubusercontent.com/invoice-x/invoice2data/master/tests/compare/AzureInterior.pdf' --header 'Authorization: Bearer YOUR_API_KEY'
{
"document_type": {
"value": "invoice",
"quote": "Invoice INV/2023/03/0008",
"confidence": 0.9
},
"vendor": {
"name": {
"value": "Global Wholesaler",
"quote": "Global Wholesaler",
"confidence": 0.95
},
"address": {
"value": "Azure Interior 4557 De Silva St Fremont CA 94538 United States",
"quote": "Azure Interior 4557 De Silva St Fremont CA 94538 United States",
"confidence": 0.95
},
"vat_id": {
"value": null,
"quote": null,
"confidence": null
},
"email": {
"value": "[email protected]",
"quote": "[email protected]",
"confidence": 0.95
},
"phone": {
"value": "(870)-931-0505",
"quote": "(870)-931-0505",
"confidence": 0.95
},
"iban": {
"value": "US1234567890",
"quote": "US1234567890",
"confidence": 0.95
}
},
"customer": {
"name": {
"value": "YourCompany",
"quote": "YourCompany, Mitchell Admin",
"confidence": 0.95
},
"address": {
"value": "215 Vine St Scranton PA 18503 United States",
"quote": "215 Vine St Scranton PA 18503 United States",
"confidence": 0.95
},
"vat_id": {
"value": null,
"quote": null,
"confidence": null
}
},
"invoice_number": {
"value": "INV/2023/03/0008",
"quote": "Invoice INV/2023/03/0008",
"confidence": 0.95
},
"order_number": {
"value": "CUSTREF123",
"quote": "Reference:CUSTREF123",
"confidence": 0.95
},
"issue_date": {
"value": "2023-03-20",
"quote": "03/20/2023",
"confidence": 0.9
},
"due_date": {
"value": "2023-04-04",
"quote": "04/04/2023",
"confidence": 0.9
},
"currency": {
"value": "USD",
"quote": "$ 112.00",
"confidence": 0.9
},
"payment_terms": {
"value": "15 Days",
"quote": "Payment terms: 15 Days",
"confidence": 0.95
},
"totals": {
"subtotal": {
"value": 262.9,
"quote": "$ 262.90",
"confidence": 0.98
},
"vat_total": {
"value": 16.94,
"quote": "$ 16.94",
"confidence": 0.98
},
"total": {
"value": 279.84,
"quote": "$ 279.84",
"confidence": 0.98
},
"amount_due": {
"value": null,
"quote": null,
"confidence": null
}
},
"vat_breakdown": [
{
"rate": 15,
"base": 112.9,
"amount": 16.94,
"quote": "$ 16.94",
"confidence": 0.85
}
],
"line_items": [
{
"description": "Beeswax XL",
"quantity": 1,
"unit_price": 42,
"amount": 42,
"vat_rate": 15,
"quote": "[17589684] Beeswax XL Acme beeswax 1.00 kg 42.00 0.00 15.00% $ 42.00",
"confidence": 0.85
},
{
"description": "Office Chair",
"quantity": 1,
"unit_price": 70,
"amount": 70,
"vat_rate": 15,
"quote": "[FURN_7777] Office Chair 1.00 Units 70.00 0.00 15.00% $ 70.00",
"confidence": 0.85
},
{
"description": "Olive Oil",
"quantity": 1,
"unit_price": 1,
"amount": 0.9,
"vat_rate": 15,
"quote": "*987123* Olive Oil 1.00 L 1.00 10.00 15.00% $ 0.90",
"confidence": 0.85
},
{
"description": "Luxury Truffles",
"quantity": 15,
"unit_price": 10,
"amount": 150,
"vat_rate": null,
"quote": "[LUX_TRF] Luxury Truffles 15.00 g 10.00 0.00 $ 150.00",
"confidence": 0.85
}
],
"checks": {
"subtotal_plus_vat_equals_total": true,
"line_items_sum_equals_subtotal_or_total": true,
"vat_breakdown_sum_equals_vat_total": true,
"due_date_not_before_issue_date": true
},
"overall_confidence": 0.94,
"missing": [
"vendor_vat_id",
"customer_vat_id",
"amount_due"
],
"pages": 1,
"billed_usd": 0.0075,
"input": "pdf",
"text_chars": 1036,
"model": "@cf/mistralai/mistral-small-3.1-24b-instruct",
"timing_ms": {
"pdf_text_ms": 719,
"extract_ms": 17579,
"total": 18298
},
"confidence_method": "Per field: 0.6 if the quote is found verbatim in the document text (+0.3 if the value matches the quote; 0.35 base if the quote is not verbatim), then +0.08/-0.15 from the arithmetic checks for totals. Values with confidence < 0.6 should be reviewed.",
"limits": "LLM extraction can misread layouts; check important values (quotes make that quick). Scanned PDFs need image input. Documents are not stored.",
"sources": [
{
"name": "Cloudflare Workers AI: toMarkdown (PDF text layer), Mistral Small 3.1 24B (OCR of images + field extraction; fallback Llama 3.3 70B / Llama 4 Scout / Gemma 3 12B)",
"url": "https://developers.cloudflare.com/workers-ai/",
"note": "Documents are processed in memory and not stored or logged. No third-party LLM API."
}
]
}
curl --location --request POST 'https://zylalabs.com/api/14523/invoice+and+text+to+json+extraction+api/37077/invoice+to+json+post' --header 'Authorization: Bearer YOUR_API_KEY'
--data-raw '{"url":"https://raw.githubusercontent.com/invoice-x/invoice2data/master/tests/compare/AzureInterior.pdf"}'
{
"data": {
"order_id": "4471",
"company": "ACME GmbH",
"total": 1299,
"currency": "EUR",
"due_date": "2026-11-30",
"email": "[email protected]"
},
"method": "workers-ai",
"model": "@cf/meta/llama-3.1-8b-instruct-fp8-fast",
"missing": [],
"not_verbatim_in_text": [],
"limits": "Small-model / heuristic extraction; check important values. Text is not stored.",
"sources": [
{
"name": "Cloudflare Workers AI (Llama 3.1 8B fp8-fast, fallback Llama 3.3 70B / Mistral Small 3.1, JSON mode)",
"url": "https://developers.cloudflare.com/workers-ai/"
}
]
}
curl --location --request GET 'https://zylalabs.com/api/14523/invoice+and+text+to+json+extraction+api/37078/text+to+json?text=Order #4471 from ACME GmbH, total EUR 1.299,00, due 2026-11-30, contact [email protected]&schema={"type":"object","properties":{"order_id":{"type":"string"},"company":{"type":"string"},"total":{"type":"number"},"currency":{"type":"string"},"due_date":{"type":"string","format":"date"},"email":{"type":"string","format":"email"}}}' --header 'Authorization: Bearer YOUR_API_KEY'
{
"data": {
"order_id": "4471",
"total": 1299
},
"method": "workers-ai",
"model": "@cf/meta/llama-3.1-8b-instruct-fp8-fast",
"missing": [],
"not_verbatim_in_text": [],
"limits": "Small-model / heuristic extraction; check important values. Text is not stored.",
"sources": [
{
"name": "Cloudflare Workers AI (Llama 3.1 8B fp8-fast, fallback Llama 3.3 70B / Mistral Small 3.1, JSON mode)",
"url": "https://developers.cloudflare.com/workers-ai/"
}
]
}
curl --location --request POST 'https://zylalabs.com/api/14523/invoice+and+text+to+json+extraction+api/37079/text+to+json+post' --header 'Authorization: Bearer YOUR_API_KEY'
--data-raw '{"text":"Order ID: 4471, Total: EUR 1.299,00","schema":{"type":"object","properties":{"order_id":{"type":"string"},"total":{"type":"number"}}}}'
Después de registrarte, a cada desarrollador se le asigna una clave de acceso a la API personal, una combinación única de letras y dígitos proporcionada para acceder a nuestro endpoint de la API. Para autenticarte con el Extracción de facturas y texto a JSON API simplemente incluye tu token de portador en el encabezado de Autorización.
| Encabezado | Descripción |
|---|---|
Autorización
|
Requerido
Debería ser Bearer access_key. Consulta "Tu Clave de Acceso a la API" arriba cuando estés suscrito.
|
Sin compromiso a largo plazo. Mejora, reduce o cancela en cualquier momento. La Prueba Gratuita incluye hasta 50 solicitudes.
Convierte facturas recibos y texto no estructurado en JSON estructurado con puntajes de confianza
Los endpoints de Factura a JSON devuelven datos JSON estructurados de facturas y recibos que incluyen detalles del proveedor información del cliente números de factura y totales financieros Los endpoints de Texto a JSON devuelven JSON limpio basado en la entrada de texto desordenada estructurada de acuerdo con un esquema definido por el usuario
Los campos clave en la respuesta de Invoice a JSON incluyen nombre del proveedor, dirección, ID de IVA, correo electrónico, teléfono, número de factura, fecha de emisión, moneda, subtotal, total de IVA y líneas de artículos. Para Texto a JSON, los campos clave dependen del esquema proporcionado, como ID de pedido, total y fecha de vencimiento
Los datos devueltos están en formato JSON estructurado con pares clave-valor Para las facturas sigue un esquema fijo con objetos anidados para los detalles del vendedor y del cliente Las respuestas de texto a JSON están estructuradas según el esquema definido por el usuario asegurando la consistencia de tipos
Los endpoints de Factura a JSON proporcionan información detallada sobre facturas y recibos, incluyendo datos del vendedor y del cliente, totales financieros y líneas de artículos. Los endpoints de Texto a JSON extraen datos relevantes de texto no estructurado basado en un esquema específico
Los usuarios pueden enviar parámetros como {url}, {file_base64, mime_type} o {text} para los puntos finales de Factura a JSON. Para Texto a JSON, los usuarios proporcionan texto desordenado y un esquema JSON. Las solicitudes GET también pueden usar parámetros ?url= o ?text=
Los datos de respuesta están organizados en objetos JSON estructurados Cada campo clave contiene un valor una cita textual de la fuente y un puntaje de confianza Esta organización permite a los usuarios acceder e interpretar fácilmente la información extraída
La precisión de los datos se mantiene a través de puntajes de confianza para cada campo extraído que indican la confiabilidad de la información Los controles aritméticos aseguran que los totales coincidan y el uso de modelos de inteligencia artificial avanzados mejora la calidad de la extracción
Los casos de uso típicos incluyen la automatización del procesamiento de facturas la extracción de información clave de los recibos para contabilidad y la conversión de texto no estructurado en datos estructurados para análisis Los usuarios pueden agilizar la entrada de datos y mejorar la precisión en los registros financieros