Mindee website screenshot

Mindee

Mindee is a document parsing and intelligent document processing platform. Its REST API (api-v2.mindee.net) provides asynchronous inference across five model families — Extraction, Classification, Crop, OCR, and Split — plus a unified Jobs endpoint for polling. Mindee ships prebuilt models for invoices, receipts, passports, IDs, resumes, bank statements, and barcodes, along with customer-configurable extraction models with their own Data Schemas. Native SDKs cover Python, Node.js, Java, PHP, Ruby, and .NET, and front-end vision SDKs cover React and Vue. Mindee also stewards the open-source docTR OCR library.

Mindee publishes 6 APIs on the APIs.io network, including Extraction API, Classification API, Crop API, and 3 more. Tagged areas include Document Parsing, OCR, IDP, AI, and Machine Learning.

The Mindee catalog on APIs.io includes 1 JSON-LD context and 2 Spectral governance rulesets.

Mindee’s developer surface includes authentication, developer portal, documentation, getting-started guide, signup flow, pricing, engineering blog, and 48 more developer resources.

59.8/100 strong ▬ flat Agent 50/100 agent ready Full breakdown ↓
scored 2026-07-28 · rubric v0.6
AccessPaidSelf serve
6 APIs 15 Features
Document ParsingOCRIDPAIMachine LearningInvoicesReceiptsIDsComputer Vision

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-28 · rubric v0.6
Composite quality — 59.8/100 · strong
Contract Quality 19.2 / 25
Developer Ergonomics 12.2 / 20
Commercial Clarity 10.0 / 20
Operational Transparency 3.8 / 13
Governance 8.3 / 12
Discoverability 6.5 / 10
Agent readiness — 50/100 · agent ready
Machine-Readable Contract 18 / 18
Agentic Access Contract 10 / 10
MCP Server 0 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 7 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 6 / 6
Agent Skills 0 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
A2A Agent Card 0 / 8
Dry-Run / Simulate Mode 0 / 4
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/mindee: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 6

Individual APIs this provider publishes, each with its own machine-readable definition.

Mindee Extraction API

Extract structured fields from invoices, receipts, IDs, passports, resumes, bank statements, and any other document type via Mindee's configurable extraction models. Enqueue a f...

Mindee Classification API

Classify documents into predefined categories so they can be routed to the appropriate downstream extraction model. Enqueue at POST /v2/products/classification/enqueue and retri...

Mindee Crop API

Detect, isolate, and crop the document area inside a larger scanned image. Useful for cleaning up phone-captured documents prior to classification or extraction. Async enqueue/r...

Mindee OCR API

Run full-page optical character recognition on a document and return the raw text plus bounding polygons. Enqueue at POST /v2/products/ocr/enqueue and retrieve the OCR payload f...

Mindee Split API

Split a multi-document PDF or image batch into individual documents that can each be classified and extracted independently. Async enqueue/results pattern at /v2/products/split/.

Mindee Jobs API

Poll the status of asynchronous Mindee inference jobs across every Mindee model family via GET /v2/jobs/{job_id}. Jobs return Waiting, Processing, Failed, or Success states and ...

Postman Collections 6

Ready-to-run Postman collections for exercising this provider's APIs.

Open Collections 6

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

Mindee Classification API

OPEN COLLECTION

Mindee Crop API

OPEN COLLECTION

Mindee Extraction API

OPEN COLLECTION

Mindee Jobs API

OPEN COLLECTION

Mindee OCR API

OPEN COLLECTION

Mindee Split API

OPEN COLLECTION

Arazzo Workflows 14

Multi-step API workflows described with the Arazzo specification.

Mindee Bank Statement Extraction

Enqueue a bank statement with RAG and raw text enabled, poll until processed, then read the extracted transactions and balances.

ARAZZO

Mindee Classify Document Type

Enqueue a document for classification, poll until processed, then read the predicted document type.

ARAZZO

Mindee Classify Then Extract

Classify an unknown document, then run extraction on the same file once the type is known, reading the parsed fields.

ARAZZO

Mindee Crop Document

Enqueue a document for cropping, poll until processed, then read the detected objects and their crop coordinates.

ARAZZO

Mindee Custom Document Extraction

Enqueue an arbitrary document against a custom model with raw text capture, poll until processed, then read fields and full text.

ARAZZO

Mindee Extract From URL

Enqueue a publicly hosted document by URL for extraction, poll until processed, then read the extracted fields.

ARAZZO

Mindee Invoice Extraction

Enqueue an invoice for extraction, poll the job until processed, then read the extracted fields.

ARAZZO

Mindee OCR Full Text

Enqueue a document for full-page OCR, poll until processed, then read the per-page words and text content.

ARAZZO

Mindee OCR Then Extract

Run OCR over a document to capture its raw text, then extract structured fields from the same file, reading both outputs.

ARAZZO

Mindee Passport and ID Extraction

Enqueue a passport or identity document with polygon locations, poll until processed, then read the extracted holder fields.

ARAZZO

Mindee Poll Job With Failure Branch

Enqueue an extraction, poll the job, and branch explicitly on Processed, Processing, or Failed before reading the result.

ARAZZO

Mindee Receipt Extraction

Enqueue a receipt with confidence scoring, poll until processed, then read the extracted line items and totals.

ARAZZO

Mindee Split Multi-Document File

Enqueue a multi-document file for splitting, poll until processed, then read the identified document ranges.

ARAZZO

Mindee Split Then Extract

Split a multi-document file into ranges, then extract structured fields from the original file, reading splits and fields.

ARAZZO

Scroll for all 14

Pricing Plans 1

Published pricing tiers and plan structures.

Mindee Plans Pricing

4 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Mindee Rate Limits

0 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals for API financial operations.

Features 15

Notable capabilities this provider offers.

Async enqueue/results pattern across all Mindee models with a unified job polling endpoint
Configurable extraction models with customer-defined Data Schemas
Library of ready-to-use models for invoices, receipts, IDs, passports, driver's licenses, resumes, bank statements, and barcodes
Classification, Crop, OCR, and Split utility models for full IDP pipelines
Continuous Learning via Retrieval-Augmented Generation against a customer knowledge base
Confidence scores and bounding polygons (Pro and higher)
Full raw OCR text option on extraction inferences
100 MB file size limit; up to 200 pages per PDF
Webhook-based result delivery in addition to polling
Per-model and per-API-key usage insights inside the platform console
Native SDKs for Python, Node.js, Java, PHP, Ruby, and .NET
Front-end computer vision SDKs for React and Vue
Open-source docTR library for self-hosted OCR
Zapier and Microsoft Flow integrations for no-code automation
Credit-based pricing with monthly subscription tiers and per-credit overage

Scroll for all 15

Semantic Vocabularies 1

JSON-LD contexts and semantic vocabularies used across these APIs.

Mindee Context

11 classes · 14 properties

JSON-LD

Spectral Rules 2

Spectral governance rulesets for linting and validating these APIs.

Mindee API Rules

5 rules · 4 warnings 1 info

SPECTRAL

Mindee API Rules

6 rules · 3 errors 2 warnings 1 info

SPECTRAL

JSON Schema 2

Standalone JSON Schema definitions for this provider's data models.

Mindee Inference

1 properties

JSON SCHEMA

Mindee Job

1 properties

JSON SCHEMA

JSON Structure 1

JSON Structure definitions describing this provider's data shapes.

Mindee Extraction Structure

1 properties

JSON STRUCTURE

Examples 2

Example request and response payloads for these APIs.

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Mindee Authentication

apiKey · 1 scheme

SECURITY

Mindee Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Mindee Agentic Access

13 operations · 6 acting

13 operations · 6 acting

AGENTIC

Resources

Get Started 3

Portal, sign-up, and the first successful call

Documentation 6

Reference material describing how the API behaves

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 18

Pagination, idempotency, versioning, errors, and events

Scroll for all 18

Build 10

SDKs, sample code, and the tooling you integrate with

Scroll for all 10

Access & Security 4

Authentication, authorization, and security posture

Operate 4

Status, limits, changes, and where to get help

Commercial 3

Pricing, plans, and the legal terms of use

Company 5

The organization behind the API

Other 1

Properties that don't map to a standard resource type

Source (apis.yml)

apis.yml Raw ↑
aid: mindee
url: https://raw.githubusercontent.com/api-evangelist/mindee/refs/heads/main/apis.yml
apis:
- aid: mindee:mindee-extraction-api
  name: Mindee Extraction API
  tags:
  - Document Parsing
  - OCR
  - Extraction
  - Invoices
  - Receipts
  - IDP
  humanURL: https://docs.mindee.com/extraction-models/data-schema
  properties:
  - url: https://docs.mindee.com/extraction-models/data-schema
    type: Documentation
  - url: https://docs.mindee.com/integrations/api-overview
    type: Documentation
  - url: openapi/mindee-extraction-api-openapi.yml
    type: OpenAPI
  - url: json-schema/mindee-inference-schema.json
    type: JSONSchema
  - url: json-structure/mindee-extraction-structure.json
    type: JSONStructure
  - url: json-ld/mindee-context.jsonld
    type: JSONLD
  - url: examples/mindee-extraction-enqueue-example.json
    type: Examples
  - url: examples/mindee-extraction-result-example.json
    type: Examples
  description: Extract structured fields from invoices, receipts, IDs, passports, resumes, bank statements, and any other
    document type via Mindee's configurable extraction models. Enqueue a file at POST /v2/inferences/enqueue (or POST /v2/products/extraction/enqueue),
    reference your model_id, and retrieve the structured JSON result from GET /v2/inferences/{inference_id}. Supports RAG,
    raw text, polygons, and confidence scores depending on plan.
- aid: mindee:mindee-classification-api
  name: Mindee Classification API
  tags:
  - Document Parsing
  - Classification
  - Routing
  - IDP
  humanURL: https://docs.mindee.com/classification-models/classification-overview
  properties:
  - url: https://docs.mindee.com/classification-models/classification-overview
    type: Documentation
  - url: openapi/mindee-classification-api-openapi.yml
    type: OpenAPI
  description: Classify documents into predefined categories so they can be routed to the appropriate downstream extraction
    model. Enqueue at POST /v2/products/classification/enqueue and retrieve the label from GET /v2/products/classification/results/{inference_id}.
- aid: mindee:mindee-crop-api
  name: Mindee Crop API
  tags:
  - Document Parsing
  - Cropping
  - Preprocessing
  - IDP
  humanURL: https://docs.mindee.com/crop-models/crop-overview
  properties:
  - url: https://docs.mindee.com/crop-models/crop-overview
    type: Documentation
  - url: openapi/mindee-crop-api-openapi.yml
    type: OpenAPI
  description: Detect, isolate, and crop the document area inside a larger scanned image. Useful for cleaning up phone-captured
    documents prior to classification or extraction. Async enqueue/results pattern at /v2/products/crop/.
- aid: mindee:mindee-ocr-api
  name: Mindee OCR API
  tags:
  - OCR
  - Document Parsing
  - Text Extraction
  humanURL: https://docs.mindee.com/ocr-models/ocr-overview
  properties:
  - url: https://docs.mindee.com/ocr-models/ocr-overview
    type: Documentation
  - url: openapi/mindee-ocr-api-openapi.yml
    type: OpenAPI
  description: Run full-page optical character recognition on a document and return the raw text plus bounding polygons. Enqueue
    at POST /v2/products/ocr/enqueue and retrieve the OCR payload from GET /v2/products/ocr/results/{inference_id}.
- aid: mindee:mindee-split-api
  name: Mindee Split API
  tags:
  - Document Parsing
  - Splitting
  - Preprocessing
  - IDP
  humanURL: https://docs.mindee.com/split-models/split-overview
  properties:
  - url: https://docs.mindee.com/split-models/split-overview
    type: Documentation
  - url: openapi/mindee-split-api-openapi.yml
    type: OpenAPI
  description: Split a multi-document PDF or image batch into individual documents that can each be classified and extracted
    independently. Async enqueue/results pattern at /v2/products/split/.
- aid: mindee:mindee-jobs-api
  name: Mindee Jobs API
  tags:
  - Document Parsing
  - Jobs
  - Async
  - Polling
  humanURL: https://docs.mindee.com/integrations/polling-for-results
  properties:
  - url: https://docs.mindee.com/integrations/polling-for-results
    type: Documentation
  - url: https://docs.mindee.com/integrations/webhooks
    type: Documentation
  - url: openapi/mindee-jobs-api-openapi.yml
    type: OpenAPI
  - url: json-schema/mindee-job-schema.json
    type: JSONSchema
  description: Poll the status of asynchronous Mindee inference jobs across every Mindee model family via GET /v2/jobs/{job_id}.
    Jobs return Waiting, Processing, Failed, or Success states and a polling_url plus optional result_url and webhook_url.
name: Mindee
tags:
- Document Parsing
- OCR
- IDP
- AI
- Machine Learning
- Invoices
- Receipts
- IDs
- Computer Vision
kind: contract
accessModel:
  pricing: paid
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Paid · Self-serve signup
  confidence: high
  source:
  - plans
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/mindee.png
access: 3rd-Party
common:
- type: AgenticAccess
  url: agentic-access/mindee-agentic-access.yml
- type: DomainSecurity
  url: security/mindee-domain-security.yml
- type: Authentication
  url: authentication/mindee-authentication.yml
- type: PostmanWorkspace
  url: https://www.postman.com/kinlaneapi/mindee/overview
- type: Arazzo
  url: arazzo/mindee-bank-statement-extraction-workflow.yml
  name: Mindee Bank Statement Extraction
- type: Arazzo
  url: arazzo/mindee-classify-document-type-workflow.yml
  name: Mindee Classify Document Type
- type: Arazzo
  url: arazzo/mindee-classify-then-extract-workflow.yml
  name: Mindee Classify Then Extract
- type: Arazzo
  url: arazzo/mindee-crop-document-workflow.yml
  name: Mindee Crop Document
- type: Arazzo
  url: arazzo/mindee-custom-document-extraction-workflow.yml
  name: Mindee Custom Document Extraction
- type: Arazzo
  url: arazzo/mindee-extract-from-url-workflow.yml
  name: Mindee Extract From URL
- type: Arazzo
  url: arazzo/mindee-invoice-extraction-workflow.yml
  name: Mindee Invoice Extraction
- type: Arazzo
  url: arazzo/mindee-ocr-full-text-workflow.yml
  name: Mindee OCR Full Text
- type: Arazzo
  url: arazzo/mindee-ocr-then-extract-workflow.yml
  name: Mindee OCR Then Extract
- type: Arazzo
  url: arazzo/mindee-passport-id-extraction-workflow.yml
  name: Mindee Passport and ID Extraction
- type: Arazzo
  url: arazzo/mindee-poll-job-with-failure-branch-workflow.yml
  name: Mindee Poll Job With Failure Branch
- type: Arazzo
  url: arazzo/mindee-receipt-extraction-workflow.yml
  name: Mindee Receipt Extraction
- type: Arazzo
  url: arazzo/mindee-split-multi-document-workflow.yml
  name: Mindee Split Multi-Document File
- type: Arazzo
  url: arazzo/mindee-split-then-extract-workflow.yml
  name: Mindee Split Then Extract
- type: Portal
  url: https://mindee.com
- type: Documentation
  url: https://docs.mindee.com
- url: https://docs.mindee.com/getting-started/quick-start
  name: Quick Start
  type: GettingStarted
- url: https://docs.mindee.com/integrations/api-overview
  name: API Overview
  type: Documentation
- url: https://docs.mindee.com/integrations/api-keys
  name: API Keys
  type: Authentication
- url: https://docs.mindee.com/integrations/webhooks
  name: Webhooks
  type: Webhooks
- url: https://docs.mindee.com/integrations/polling-for-results
  name: Polling for Results
  type: Documentation
- url: https://docs.mindee.com/integrations/problem-database
  name: Problem Database
  type: ErrorCodes
- url: https://docs.mindee.com/integrations/technical-limitations
  name: Technical Limitations
  type: RateLimits
- url: https://docs.mindee.com/integrations/response-times
  name: Response Times
  type: Documentation
- url: https://api-v2.mindee.net/openapi.json
  name: Mindee V2 OpenAPI
  type: OpenAPI
- url: https://app.mindee.com
  name: Mindee Platform
  type: Signup
- url: https://app.mindee.com/api-keys
  name: API Keys Console
  type: Authentication
- url: https://status.mindee.com
  type: StatusPage
- url: https://mindee.com/pricing
  name: Pricing
  type: Pricing
  data:
  - id: starter
    name: Starter
    entries:
    - geo: global
      unit: 1
      label: User
      limit: 1
      price: 44
      currency: EUR
      metric: subscription
      timeFrame: month
      description: 500 credits per month with community support.
    elements:
    - name: 500 credits per month
    - name: Unlimited models
    - name: Community support
    - name: 0.05 EUR per credit overage
    description: Entry-level plan with community support.
  - id: pro
    name: Pro
    entries:
    - geo: global
      unit: 1
      label: User
      limit: 1
      price: 179
      currency: EUR
      metric: subscription
      timeFrame: month
      description: 2,500 credits per month with live chat support and polygons.
    elements:
    - name: 2,500 credits per month
    - name: Live chat support
    - name: Team members
    - name: Data processing localization
    - name: RAG (up to 20 documents)
    - name: Polygons
    - name: 0.04 EUR per credit overage
    description: Most popular plan with collaboration and RAG.
  - id: business
    name: Business
    entries:
    - geo: global
      unit: 1
      label: User
      limit: 1
      price: 584
      currency: EUR
      metric: subscription
      timeFrame: month
      description: 10,000 credits per month with confidence scores and boosted accuracy.
    elements:
    - name: 10,000 credits per month
    - name: All Pro features
    - name: Unlimited RAG
    - name: Confidence scores
    - name: Boosted accuracy and precision
    - name: 0.035 EUR per credit overage
    description: Volume plan with full feature set.
  - id: enterprise
    name: Enterprise
    entries:
    - geo: global
      unit: 1
      label: User
      limit: 1
      price: Call
      currency: EUR
      metric: contract
      timeFrame: year
      description: Custom contract for organizations using 250k+ credits annually.
    elements:
    - name: Dedicated account manager
    - name: Custom SLAs
    - name: Premium technical support
    - name: Custom models
    - name: All Business features
    description: For organizations operating at scale.
- url: https://mindee.com/blog
  type: Blog
- url: https://mindee.com/about
  type: AboutUs
- url: https://mindee.com/careers
  type: Careers
- url: https://mindee.com/contact
  type: Contact
- url: https://www.linkedin.com/company/mindee
  type: LinkedIn
- url: https://twitter.com/mindee_official
  type: Twitter
- url: https://github.com/mindee
  type: GitHubOrganization
- url: https://github.com/mindee/mindee-api-python
  name: Python SDK
  type: SDKs
- url: https://github.com/mindee/mindee-api-nodejs
  name: Node.js SDK
  type: SDKs
- url: https://github.com/mindee/mindee-api-java
  name: Java SDK
  type: SDKs
- url: https://github.com/mindee/mindee-api-php
  name: PHP SDK
  type: SDKs
- url: https://github.com/mindee/mindee-api-ruby
  name: Ruby SDK
  type: SDKs
- url: https://github.com/mindee/mindee-api-dotnet
  name: .NET SDK
  type: SDKs
- url: https://github.com/mindee/react-mindee-js
  name: React Computer Vision SDK
  type: SDKs
- url: https://github.com/mindee/vue-mindee-js
  name: Vue Computer Vision SDK
  type: SDKs
- url: https://github.com/mindee/doctr
  name: docTR (Open-source OCR)
  type: OpenSource
- url: https://github.com/mindee/integration-zapier
  name: Zapier Integration
  type: Integrations
- url: https://github.com/mindee/integration-microsoft-flow
  name: Microsoft Flow Integration
  type: Integrations
- url: https://github.com/mindee/platform-docs
  name: Platform Documentation Repository
  type: Documentation
- url: plans/mindee-plans-pricing.yml
  type: Plans
- url: rate-limits/mindee-rate-limits.yml
  type: RateLimits
- url: finops/mindee-finops.yml
  type: FinOps
- url: vocabulary/mindee-vocabulary.yml
  type: Vocabulary
- url: rules/mindee-rules.yml
  type: SpectralRules
- type: Features
  data:
  - Async enqueue/results pattern across all Mindee models with a unified job polling endpoint
  - Configurable extraction models with customer-defined Data Schemas
  - Library of ready-to-use models for invoices, receipts, IDs, passports, driver's licenses, resumes, bank statements, and
    barcodes
  - Classification, Crop, OCR, and Split utility models for full IDP pipelines
  - Continuous Learning via Retrieval-Augmented Generation against a customer knowledge base
  - Confidence scores and bounding polygons (Pro and higher)
  - Full raw OCR text option on extraction inferences
  - 100 MB file size limit; up to 200 pages per PDF
  - Webhook-based result delivery in addition to polling
  - Per-model and per-API-key usage insights inside the platform console
  - Native SDKs for Python, Node.js, Java, PHP, Ruby, and .NET
  - Front-end computer vision SDKs for React and Vue
  - Open-source docTR library for self-hosted OCR
  - Zapier and Microsoft Flow integrations for no-code automation
  - Credit-based pricing with monthly subscription tiers and per-credit overage
  sources:
  - https://mindee.com
  - https://mindee.com/pricing
  - https://docs.mindee.com
  - https://api-v2.mindee.net/openapi.json
  updated: '2026-05-25'
created: '2026-05-25'
modified: '2026-05-25'
position: Consuming
description: Mindee is a document parsing and intelligent document processing platform. Its REST API (api-v2.mindee.net) provides
  asynchronous inference across five model families — Extraction, Classification, Crop, OCR, and Split — plus a unified Jobs
  endpoint for polling. Mindee ships prebuilt models for invoices, receipts, passports, IDs, resumes, bank statements, and
  barcodes, along with customer-configurable extraction models with their own Data Schemas. Native SDKs cover Python, Node.js,
  Java, PHP, Ruby, and .NET, and front-end vision SDKs cover React and Vue. Mindee also stewards the open-source docTR OCR
  library.
maintainers:
- FN: Kin Lane
  email: info@apievangelist.com
  X: apievangelist
  url: https://apievangelist.com
specificationVersion: '0.16'