Skip to main content

​
Base URL

All API requests should be made to: 
https://api.parsefy.io

​
Endpoints

MethodEndpointDescriptionAuth Required
POST/v1/extractExtract data from documentsYes
POST/v1/playgroundTest extraction (rate limited)No
GET/healthHealth checkNo
GET/API informationNo

​
Request Format

All document extraction requests use multipart/form-data encoding: 
curl -X POST "https://api.parsefy.io/v1/extract" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "[email protected]" \
  -F 'output_schema={"type": "object", "properties": {...}}'

​
Parameters

ParameterTypeDescription
fileFileThe document to process (PDF or DOCX, max 10MB)
output_schemaStringJSON Schema defining the extraction structure

​
Response Format

All successful responses follow this structure: 
{
  "object": {
    // Your extracted data matching the schema
    "_meta": {
      "confidence_score": 0.95,
      "issues": []
    }
  },
  "metadata": {
    "processing_time_ms": 2340,
    "input_tokens": 1520,
    "output_tokens": 89,
    "credits": 1,
    "fallback_triggered": false
  }
}

​
Response Fields

​
object
object
required
The extracted data matching your schema structure.
​
metadata
object
required
Processing information for the request.

​
Content Types

​
Request

  • Content-Type: multipart/form-data

​
Response

  • Content-Type: application/json

​
Supported File Types

FormatExtensionMax SizeProcessing
PDF.pdf10 MBNative multimodal AI
Microsoft Word.docx10 MBMarkdown conversion

​
SDKs

We provide official SDKs for popular languages:

Python

Use Pydantic models for type-safe extraction

Node.js

Use Zod schemas with full TypeScript support

Authentication

API key setup and usage

Rate Limits

Request and credit limits

Errors

Error codes and handling