Install Jentic One Beta

Connect the Document Recognition API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Document Recognition 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.

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%2Fdoc.cheap%2Fdoc" | sh

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%2Fdoc.cheap%2Fdoc" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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 Document Recognition API.

Recognize a document and return its extracted contents

List recent scans and fetch a previous scan by id

Delete a stored scan from the account

Report the account balance and usage for the current billing period

Issue a short-lived client token for browser or device uploads

GET STARTED

Start building with Document Recognition API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Document Recognition API for, with concrete tasks.

★ Agent Document Intake

An AI agent connected through Jentic submits an uploaded document to doc.cheap, waits for recognition, and reads the extracted contents into the workflow. The API returns the scan result and a billing flag so the agent knows whether the document was recognized, and Jentic injects the bearer token at call time.

Submit an invoice image to doc.cheap, fetch the resulting scan, and read the extracted fields

Scan History and Cleanup

Teams processing many documents list recent scans, retrieve a specific result, and delete scans they no longer need. The doc.cheap API exposes scan listing, fetch-by-id, and delete so a workflow can keep stored results tidy.

List recent scans, fetch one by its id, and delete it once its data has been saved

Usage Monitoring

Because recognition is billed per document, teams watch their balance and usage for the period. The doc.cheap API reports the current balance and usage so an agent can check remaining credits before a large batch.

Fetch the current usage and balance for the period and stop processing if credits are low

Key Endpoints

6 endpoints — the doc.

METHOD

PATH

DESCRIPTION

POST

/v1/scans

Recognize a document

GET

/v1/scans

List recent scans

GET

/v1/scans/{id}

Fetch a previous scan

DELETE

/v1/scans/{id}

Delete a stored scan

GET

/v1/usage

Balance and usage for the current period

POST

/v1/client-tokens

Issue a short-lived client token

POST

/v1/scans

Recognize a document

GET

/v1/scans

List recent scans

GET

/v1/scans/{id}

Fetch a previous scan

DELETE

/v1/scans/{id}

Delete a stored scan

GET

/v1/usage

Balance and usage for the current period

POST

/v1/client-tokens

Issue a short-lived client token

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring doc.cheap by hand means managing its bearer token, deciding when to mint short-lived client tokens for uploads, and tracking per-document billing yourself. Through Jentic you install once, import doc.cheap from the API Directory, store the token once, and your agent calls it.

Permission scoping

Limit the agent to the operations it needs, such as recognizing documents and listing scans, so destructive operations like deleting a stored scan or issuing client tokens are not included unless you add them.

Credential isolation

Your doc.cheap token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'recognize a document' or 'check my usage', and Jentic returns the matching doc.cheap operation with its input schema so the agent calls the right endpoint directly.

FAQs

Specific to using Document Recognition API through Jentic.

What authentication does the doc.cheap API use?

The doc.cheap API authenticates with a bearer token sent in the Authorization header, per its OpenAPI spec. You can also issue a short-lived client token for direct browser or device uploads. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at execution time, so it never enters the agent's prompt or logs.

Can I extract data from documents with the doc.cheap API?

Yes. Submit a document to the recognition endpoint and the API returns its extracted contents along with a billing flag that indicates whether the document was recognized. You can then list, fetch, or delete the stored scan and check your remaining balance.

Is there a doc.cheap MCP server?

You don't need an MCP server to give your agent the doc.cheap API. Jentic connects it directly from the API Directory: import it, store your bearer token once, and your agent calls the scan and usage operations. Operations load on demand, so your agent's context stays lean instead of holding another server's tool definitions.

Can I limit what my agent is allowed to do with the doc.cheap API?

Yes. Write a rule that allows only the recognize and list-scans operations, so the agent can submit documents and read results but cannot delete stored scans or issue client tokens. Every call the agent makes is logged.

What are the rate limits for the doc.cheap API?

The OpenAPI spec does not specify rate limits; recognition is billed per recognized document with a free monthly allowance described in the spec. Check the doc.cheap documentation at https://doc.cheap for current limits and pricing before running a large batch.

How do I recognize a document with the doc.cheap API through Jentic?

Search Jentic for an intent like 'recognize a document', add the doc.cheap API from the directory, and store your bearer token once. Your agent then submits the document and reads the extracted contents from the scan result. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Doc Cheap Document Recognition API

AI ReadinessAI-Aware (A-)74/100

See full scorecard

Official vendor OpenAPI document · agent-readyAI/MLVisionbearer6 EndpointsREST

For Agents

Recognize documents and extract their contents with doc.cheap: submit a scan, list and fetch past scans, delete a stored scan, check usage, and issue client upload tokens.

Use for: Recognize the text and fields in a scanned document, I need to extract data from a receipt image, List my recent document scans, Retrieve a previous scan by its id

Not supported: Does not handle document generation, e-signatures, or long-term file archival. Use for recognizing documents and extracting their contents only.

The doc.cheap API recognizes documents and returns their extracted contents, charging only when a document is actually recognized. It submits a document for recognition, lists recent scans, fetches or deletes a stored scan by id, and reports the account balance and usage for the current period. A short-lived client token lets browsers or devices upload directly.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

100

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

98%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

100%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: A-Signals: 4

25%

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

75%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: C+Signals: 4

72%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

64%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: B-Signals: 1

60%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: ASignals: 1

81%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Document Recognition API to your agent

Capabilities

Start building with Document Recognition API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Doc Cheap Document Recognition API

Jentic AI Readiness Score

Document Recognition API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness