> ## Documentation Index
> Fetch the complete documentation index at: https://docs.documind.cloud/llms.txt
> Use this file to discover all available pages before exploring further.

# API Overview

> Intelligent document extraction API for automation workflows

## What is Documind API?

Documind provides a powerful document extraction API designed for automation developers and integration engineers. Upload documents, define extraction schemas, and receive structured JSON data with confidence scores and automatic review flagging.

## Key Capabilities

<CardGroup cols={2}>
  <Card title="Multi-Model Extraction" icon="brain">
    Choose between Basic, VLM-based, or Advanced (multi-model ensemble) extraction modes with different accuracy and speed trade-offs.
  </Card>

  <Card title="Schema Flexibility" icon="table">
    Use predefined schemas, generate from samples, or create custom schemas for any document type.
  </Card>

  <Card title="Review Workflow" icon="flag">
    Automatic flagging of low-confidence fields enables human-in-the-loop validation for critical data.
  </Card>

  <Card title="Credit-Based Usage" icon="coins">
    Transparent per-page pricing with different credit costs for Basic (2-6), VLM (10), and Advanced (15) extraction.
  </Card>
</CardGroup>

## How It Works

<Steps>
  <Step title="Upload Documents">
    Submit PDF, Word, or image files via the `/upload` endpoint. Returns document IDs for processing.
  </Step>

  <Step title="Define Schema">
    Specify what data to extract using JSON Schema format. Generate schemas automatically or use predefined templates.
  </Step>

  <Step title="Extract Data">
    Process documents with `/extract/{document_id}`. Choose extraction mode and review threshold.
  </Step>

  <Step title="Handle Reviews">
    Poll `/data/extractions` to detect when `is_reviewed=true` for documents that needed review. Use corrected data in your automation.
  </Step>
</Steps>

## Extraction Modes

<AccordionGroup>
  <Accordion title="Basic Extraction (2-6 credits/page)">
    Single-model extraction with your choice of:

    * `google-gemini-3-flash` (6 credits)
    * `google-gemini-2.5-flash` (4 credits)
    * `qwen-3-vl` (2 credits)

    Best for simple documents where extensive validation isn't required.
  </Accordion>

  <Accordion title="VLM Based Extraction (10 credits/page)">
    Uses native visual data to process content through multiple Vision-Language Models.

    Best for low-text, high-visual content like scanned documents, images, or forms where layout is crucial.
  </Accordion>

  <Accordion title="Advanced Extraction (15 credits/page)">
    Multi-model ensemble extraction utilizing document layout, reading order, and OCR'd text.

    Includes confidence scores and automatic review flagging. Best for structured documents like invoices, forms, and tables requiring high accuracy. Activated by not setting `model` or `extraction_mode` parameters.
  </Accordion>
</AccordionGroup>

## Use Cases

### Common Use Cases

* **Invoice Processing**: Extract line items, totals, vendor details
* **Form Data Entry**: Digitize paper forms into structured data
* **Document Classification**: Identify document types and route accordingly
* **Compliance Checks**: Extract specific fields for validation

### Integration Examples

<CodeGroup>
  ```python Python theme={null}
  # Typical automation workflow
  import requests

  API_KEY = "your_api_key"
  headers = {"X-API-Key": API_KEY}

  # 1. Upload documents
  files = [("files", open("invoice1.pdf", "rb")), ("files", open("invoice2.pdf", "rb"))]
  response = requests.post("https://api.documind.cloud/api/v1/upload", headers=headers, files=files)
  doc_ids = response.json()

  # 2. Extract with schema
  for doc_id in doc_ids:
      response = requests.post(
          f"https://api.documind.cloud/api/v1/extract/{doc_id}",
          headers=headers,
          json={"schema": invoice_schema, "review_threshold": 85}
      )
      result = response.json()
      
      # 3. Check if needs review
      if result['needs_review']:
          # Direct team to UI for review, then poll for completion
          print(f"⚠️ Review needed - direct team to: https://app.documind.cloud/review")
          
          # Poll until reviewed
          while True:
              ext_response = requests.get(
                  "https://api.documind.cloud/api/v1/data/extractions",
                  headers=headers,
                  params={"document_id": doc_id, "limit": 1}
              )
              extraction = ext_response.json()["items"][0]
              if extraction["is_reviewed"]:
                  process_invoice(extraction["reviewed_results"])
                  break
              time.sleep(10)
      else:
          process_invoice(result['results'])
  ```

  ```javascript Node.js theme={null}
  // Automation pipeline with polling
  const results = await Promise.all(
    docIds.map(id => extract(id, { schema, model: 'google-gemini-2.5-flash' }))
  );

  // Filter out items needing review
  const needsReview = results.filter(r => r.needs_review);

  // Poll until reviewed
  for (const item of needsReview) {
    await pollUntilReviewed(item.document_id);
  }
  ```
</CodeGroup>

## Authentication

All API requests require authentication using API keys passed in the `X-API-Key` header:

```bash theme={null}
X-API-Key: YOUR_API_KEY
```

<Warning>
  Never commit API keys to version control. Use environment variables or secure credential storage.
</Warning>

## Rate Limits & Credits

* **API Calls**: Track usage via `/usage/current` endpoint
* **Credits**: Deducted per page/image processed
* **Daily Refresh**: Credits refresh based on your subscription tier
* **Insufficient Credits**: Returns `402 Payment Required` status

Check your current credits:

```bash theme={null}
curl https://api.documind.cloud/api/v1/usage/credits \
  -H 'X-API-Key: YOUR_API_KEY'
```

## Next Steps

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/api/quickstart">
    Get started with your first extraction in 5 minutes
  </Card>

  <Card title="Authentication" icon="key" href="/api/authentication">
    Learn how to create and manage API keys
  </Card>

  <Card title="Extraction Flow" icon="diagram-project" href="/api/extraction/extraction-flow">
    Understand the complete extraction workflow
  </Card>

  <Card title="Review Polling" icon="rotate" href="/api/review/polling-pattern">
    Implement review polling for automation pipelines
  </Card>
</CardGroup>