# Batch document extraction

Process multiple documents in parallel with a single schema.

#### Request Body

**`files`** file[] required

Array of document files to process. Maximum 50 files per batch. Each file must be under 50 MB.

**`schema`** string required

JSON schema as string. All documents will be processed with the same schema.

**`organization_id`** string required

Your organization ID.

**`prompt`** string optional

Custom extraction instructions applied to all documents.

**`model`** string optional · Defaults to `ftg-3.0`

Model selection: `ftg-3.0`, `gpt-4o`, or `gpt-4o-mini`.

**`vision_model`** string optional · Defaults to `gpt-5`

Vision analysis model for processing images and PDFs. Used for OCR and visual understanding.

## Returns

Returns a batch object with job IDs for each document. Use the job IDs to check individual extraction status.

Python

```python
import requests
import json

API_URL = "https://api.aitronos.com/v1/documents/extract/batch"
TOKEN = "your_bearer_token_here"

headers = {"Authorization": f"Bearer {TOKEN}"}

schema = {
    "properties": {
        "invoice_number": {"type": "string"},
        "total_amount": {"type": "number"}
    }
}

files = [
    ("files", open("invoice1.pdf", "rb")),
    ("files", open("invoice2.pdf", "rb")),
    ("files", open("invoice3.pdf", "rb"))
]

data = {
    "schema": json.dumps(schema),
    "organization_id": "org_abc123",
    "model": "gpt-4o-mini"
}

response = requests.post(API_URL, headers=headers, files=files, data=data)
result = response.json()

if result['success']:
    print(f"Batch submitted with {len(result['job_ids'])} jobs")
    for job_id in result['job_ids']:
        print(f"Job ID: {job_id}")
```

Bash

```bash
curl -X POST https://api.aitronos.com/v1/documents/extract/batch \
  -H "X-API-Key: $FREDDY_API_KEY" \
  -F "files=@invoice1.pdf" \
  -F "files=@invoice2.pdf" \
  -F "files=@invoice3.pdf" \
  -F 'schema={"properties":{"invoice_number":{"type":"string"},"total_amount":{"type":"number"}}}' \
  -F "organization_id=org_abc123"
```

## Response Example


```json
{
  "success": true,
  "batch_id": "batch_abc123",
  "job_ids": [
    "job_abc123def456",
    "job_def456ghi789",
    "job_ghi789jkl012"
  ],
  "total_documents": 3,
  "created_at": "2024-12-16T10:30:00Z"
}
```

## Related Resources

- [Extract Document Data](/docs/api-reference/documents/extract)
- [Get Job Status](/docs/api-reference/documents/get-job-status)
- [Document Extraction Overview](/docs/api-reference/documents/introduction)