canonical: https://jentic.com/apis/veryfi.com/veryfi

# Veryfi OCR API

Veryfi OCR API provides multi-modal data extraction from receipts, invoices, business cards, checks, contracts, tax forms, bank statements, and other documents. The API supports 91 currencies and 38 languages, offering intelligent document processing with line item extraction, classification, and fraud detection capabilities. The API exposes 17 endpoints secured with apiKey authentication.

## For AI agents

Programmatically process document, list documents. Covers 17 operations with apiKey authentication.

## Scope

Does not handle communications, crm, or developer tools - use for payments only.

## Capabilities

- Process Document
- List Documents
- Get Document
- Update Document
- Delete Document
- Add Line Item

## Use cases

### Payments Operations

Use the Veryfi OCR API to perform payments operations programmatically. The API provides 17 endpoints covering core functionality including process document, list documents, get document.

Example prompt: Call POST /documents to process document

### Automated Documents Management

Automate documents operations by combining multiple Veryfi OCR API endpoints. Agents can list documents and then get document in a single workflow.

Example prompt: Call GET /documents to list documents, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call Veryfi OCR API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey tokens manually.

Example prompt: Search Jentic for 'process document', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | /documents | Process Document |
| GET | /documents | List Documents |
| GET | /documents/{document_id} | Get Document |
| PUT | /documents/{document_id} | Update Document |
| DELETE | /documents/{document_id} | Delete Document |
| POST | /documents/{document_id}/line-items | Add Line Item |
| GET | /documents/{document_id}/line-items | List Line Items |
| DELETE | /documents/{document_id}/line-items | Delete All Line Items |

## Key resources

- **Documents** — Document processing and management operations
- **Line Items** — Line item extraction and management
- **Tags** — Document tagging and organization

## Why Jentic

- **Setup:** Wiring the Veryfi OCR API by hand means setting up its two apiKey headers, the CLIENT-ID and the AUTHORIZATION key in the apiKey username:key format, and driving the v7 partner document flow yourself. Through Jentic you install once, import the Veryfi OCR API from the API Directory, store the client id and key once, and your agent calls it.
- **Permission scoping:** Veryfi puts the document id in the URL path (/documents/{document_id}), so a rule can pin your agent to one document and the operations around it. You choose the operations it may call, so destructive ones like deleting a document or removing its line items are not included unless you add them.
- **Credential handling:** Your Veryfi client id and API key are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'process a receipt document' or 'read line items from an invoice', and Jentic returns the matching Veryfi operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Stripe** — Alternative payments API
- **Adyen** — Alternative payments API
- **Square** — Complementary payments API
- **Paypal** — Complementary payments API

## FAQ

### What authentication does the Veryfi OCR API use?

The Veryfi OCR API uses an API key passed in the `CLIENT-ID` header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.

### Can I process document with the Veryfi OCR API?

Yes. Use the POST /documents endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the Veryfi OCR API?

Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.

### How do I process document through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'process document'. Jentic returns the matching Veryfi OCR API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the Veryfi OCR API have?

The Veryfi OCR API exposes 17 endpoints covering documents, line items, tags operations.

### Can I limit what my agent is allowed to do with the Veryfi OCR API?

Yes. Jentic One is self-hosted, so your own rules decide which Veryfi operations and credentials the agent may use. Because the document id sits in the URL path (/documents/{document_id}), you can pin the agent to a single document and only the operations you approve, such as POST /documents to process a document or GET /documents to list them. Destructive calls like DELETE /documents/{document_id} or deleting a document's line items stay off unless you explicitly grant them.