Abbyy Vantage processing REST API
Agent-ready OpenAPI document · curated by JenticAI/MLVisionoauth231 EndpointsREST
Know of an official OpenAPI document? Contribute it →
For Agents
Submit documents to ABBYY Vantage skills and retrieve structured field extractions via OAuth 2.0. Use it to automate invoice, receipt, and form processing.
Use for: I need to extract line items from a PDF invoice, Submit a batch of receipts to ABBYY Vantage and get the extracted totals, List all skills available in my Vantage tenant, Add 500 vendor records to a catalog used by an invoice skill
Not supported: Does not handle e-signing, document storage as a primary system of record, or generative AI text generation - use for OCR-driven document processing and field extraction only.
Jentic publishes the only available OpenAPI specification for Vantage processing REST API, keeping it validated and agent-ready. ABBYY Vantage is an intelligent document processing platform that turns unstructured documents into structured data using configurable skills (invoices, receipts, IDs, custom forms). The Vantage processing REST API exposes 31 endpoints to start transactions, upload source files, attach catalogs, run skills, and retrieve extracted document fields. It supports the US, EU, and Australia hosting regions and is gated by OAuth 2.0.
Install Jentic One Beta
Connect the Vantage processing REST API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Vantage processing REST API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fabbyy.com%2Fabbyy" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fabbyy.com%2Fabbyy" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with Vantage processing REST API.
Start a processing transaction and attach source files for a chosen skill
Trigger skill execution and poll until extraction completes
Retrieve extracted fields, confidence scores, and the source page mapping
Manage catalogs of reference records used during extraction (e.g., vendor lists)
Search catalog records by prefix to validate extracted values
Reindex a catalog after bulk record changes
List available skills and inspect their input/output schema before processing
Use Cases
Patterns agents use Vantage processing REST API for, with concrete tasks.
★ Invoice Data Extraction
Finance teams want to convert inbound invoice PDFs into structured records ready for AP automation. The Vantage processing REST API supports the full flow: POST /transactions creates the transaction, the documents and sourceFiles endpoints attach the PDF, and the result endpoints return supplier, totals, and line items as JSON. Confidence scores let downstream systems route low-confidence rows to human review.
Create a Vantage transaction for the invoice skill, attach invoice.pdf, run the skill, and return the extracted vendor name and total amount
ID and KYC Document Processing
Compliance workflows process passports, driving licences, and national IDs to populate KYC records. ABBYY Vantage provides skills tuned to ID layouts in many countries; the REST API drives them with the same transaction-and-document pattern. Catalog endpoints can validate extracted fields against an internal allow list before the record is persisted.
Run the ID skill on a passport scan, extract the document number and expiry, and validate them against an internal catalog
Catalog-Backed Validation
Many extraction projects need to match free-text fields (vendor name, GL code, country) against a controlled list. The catalog endpoints under /catalogs/{catalogId}/records support adding, deleting, and prefix-searching records, and the reindex endpoint refreshes the search index after bulk changes. This keeps extraction outputs aligned with the customer's master data.
Add 500 supplier records to catalog ID 'suppliers', call the reindex endpoint, and verify with a prefix search for 'Acm'
Agent-Driven Document Processing via Jentic
AI agents pick up document jobs from a queue and want a single tool call to extract structured data. Through Jentic, an agent searches for an extraction intent, loads the Vantage operation, and executes the transaction lifecycle without managing OAuth refresh logic. This collapses a multi-step direct integration into a few agent calls.
Search Jentic for 'extract data from an invoice', load the Vantage skill operation, attach the file, and return structured fields
Key Endpoints
31 endpoints — jentic publishes the only available openapi specification for vantage processing rest api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
POST
/api/publicapi/v1/transactions
Create a processing transaction
POST
/api/publicapi/v1/transactions/{transactionId}/documents
Create a document inside a transaction
POST
/api/publicapi/v1/transactions/{transactionId}/documents/{documentId}/sourceFiles
Attach a source file to a document
GET
/api/publicapi/v1/skills
List available skills
GET
/api/publicapi/v1/catalogs/{catalogId}/search
Prefix-search records in a catalog
POST
/api/publicapi/v1/catalogs/{catalogId}/reindex
Reindex a catalog after bulk changes
POST
/api/publicapi/v1/transactions
Create a processing transaction
POST
/api/publicapi/v1/transactions/{transactionId}/documents
Create a document inside a transaction
POST
/api/publicapi/v1/transactions/{transactionId}/documents/{documentId}/sourceFiles
Attach a source file to a document
GET
/api/publicapi/v1/skills
List available skills
GET
/api/publicapi/v1/catalogs/{catalogId}/search
Prefix-search records in a catalog
POST
/api/publicapi/v1/catalogs/{catalogId}/reindex
Reindex a catalog after bulk changes
Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Vantage processing REST API by hand means running its OAuth 2.0 client-credentials flow, choosing the right US, EU, or Australia host, and orchestrating transaction, document, and source-file steps yourself. Through Jentic you install once, import the Vantage processing REST API from the API Directory, store the client credentials once, and your agent calls it.
Permission scoping
Vantage puts the transaction and catalog id in the URL path (/transactions/{transactionId}/documents, /catalogs/{catalogId}/search), so a rule can pin your agent to one transaction or catalog. You choose the operations it may call, so a catalog reindex is not included unless you add it.
Credential isolation
Your ABBYY Vantage OAuth client secret is stored once, encrypted, by your own Jentic One instance and used to mint and refresh access tokens at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'extract data from an invoice' or 'search a Vantage catalog', and Jentic returns the matching Vantage operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Vantage processing REST API through Jentic.
Why is there no official OpenAPI spec for Vantage processing REST API?
ABBYY publishes Vantage reference docs but not a discoverable OpenAPI specification at the catalog level. Jentic generates and maintains this spec so that AI agents and developers can call Vantage processing REST API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.
What authentication does the Vantage processing REST API use?
The API uses OAuth 2.0 via the OAuth2Security scheme. Clients exchange tenant credentials for an access token and pass it as a bearer token. Through Jentic, the OAuth secret stays in your Jentic One instance and tokens are minted at execution time, so the agent never holds the raw secret.
Can I extract data from invoices with the Vantage processing REST API?
Yes. Create a transaction with POST /api/publicapi/v1/transactions for the invoice skill, attach the file via the documents and sourceFiles endpoints, then poll the transaction until the extracted document is available with structured supplier, totals, and line-item fields.
How do I list the skills available in my Vantage tenant?
Call GET /api/publicapi/v1/skills for a list, or GET /api/publicapi/v1/skills/{skillId} for the schema of a single skill. The schema describes the input options and output fields the extraction will return.
How do I run a Vantage extraction through Jentic?
Search Jentic for 'extract data from a document', load the Vantage transaction operation, and execute it with the skill ID and file. Jentic handles OAuth refresh and returns the structured extraction once processing completes.
What hosting regions does the Vantage processing REST API support?
The spec lists three base URLs: https://vantage-us.abbyy.com, https://vantage-eu.abbyy.com, and https://vantage-au.abbyy.com. Choose the region that matches your tenant; the endpoint paths are identical across regions.
Can I limit what my agent is allowed to do with the Vantage processing REST API?
Yes. Because you run Jentic One yourself, your own rules decide which Vantage operations and credentials the agent may use. Vantage puts the transaction and catalog ID in the URL path, such as /transactions/{transactionId}/documents and /catalogs/{catalogId}/search, so a rule can pin the agent to a single transaction or catalog. You also choose the exact operations it may call, so an action like a catalog reindex stays out of reach unless you add it.
GET STARTED