reducto-ai

aid: reducto-ai
url: https://raw.githubusercontent.com/api-evangelist/reducto-ai/refs/heads/main/apis.yml
apis:
  - aid: reducto-ai:reducto-parse-api
    name: Reducto Parse API
    tags:
      - Document AI
      - Parse
      - OCR
      - LLM
      - PDF
    humanURL: https://docs.reducto.ai/parse/overview
    properties:
      - url: https://docs.reducto.ai/parse/overview
        type: Documentation
      - url: https://docs.reducto.ai/api-reference/parse
        type: APIReference
      - url: https://docs.reducto.ai/api-reference/async-parse
        type: APIReference
      - url: https://docs.reducto.ai/parse/response-format
        type: Documentation
      - url: https://docs.reducto.ai/parse/best-practices
        type: Documentation
      - url: openapi/reducto-parse-api-openapi.yml
        type: OpenAPI
      - url: json-schema/reducto-parse-schema.json
        type: JSONSchema
      - url: json-ld/reducto-context.jsonld
        type: JSON-LD
    description: >-
      Parse documents (PDFs, images, spreadsheets, slides, text files) and capture layout, structure, OCR text, tables,
      figures, equations, lists, and LLM-optimized chunks. Supports agentic OCR with error correction, intelligent
      ordering, figure summarization, embedding optimization, automatic page rotation, multilingual processing across
      100+ languages, and synchronous or asynchronous execution.
  - aid: reducto-ai:reducto-extract-api
    name: Reducto Extract API
    tags:
      - Document AI
      - Extract
      - Structured Data
      - JSON Schema
    humanURL: https://docs.reducto.ai/extract/overview
    properties:
      - url: https://docs.reducto.ai/extract/overview
        type: Documentation
      - url: https://docs.reducto.ai/api-reference/extract
        type: APIReference
      - url: https://docs.reducto.ai/api-reference/extract-async
        type: APIReference
      - url: https://docs.reducto.ai/extract/response-format
        type: Documentation
      - url: https://docs.reducto.ai/extraction/best-practices-extract
        type: Documentation
      - url: https://docs.reducto.ai/configs/extract/deep-extract
        type: Documentation
      - url: https://docs.reducto.ai/configs/extract/array-extraction
        type: Documentation
      - url: https://docs.reducto.ai/configs/extract/citations
        type: Documentation
      - url: openapi/reducto-extract-api-openapi.yml
        type: OpenAPI
      - url: json-schema/reducto-extract-schema.json
        type: JSONSchema
    description: >-
      Extract structured data from documents using a caller-supplied JSON Schema. Supports Deep Extract for harder
      documents, Array Extract for repeating sections, and Citations that pin each extracted field to a page and
      bounding box in the source document.
  - aid: reducto-ai:reducto-split-api
    name: Reducto Split API
    tags:
      - Document AI
      - Split
      - Document Classification
    humanURL: https://docs.reducto.ai/split
    properties:
      - url: https://docs.reducto.ai/split
        type: Documentation
      - url: https://docs.reducto.ai/api-reference/split
        type: APIReference
      - url: https://docs.reducto.ai/api-reference/split-async
        type: APIReference
      - url: https://docs.reducto.ai/configs/split/configuration
        type: Documentation
      - url: https://docs.reducto.ai/configs/split/deep-split
        type: Documentation
      - url: openapi/reducto-split-api-openapi.yml
        type: OpenAPI
    description: >-
      Automatically separate multi-document files and long forms into individual logical units using rules-based Split
      or Deep Split, then route each unit to downstream Parse, Extract, or Edit operations inside a Pipeline.
  - aid: reducto-ai:reducto-edit-api
    name: Reducto Edit API
    tags:
      - Document AI
      - Edit
      - Forms
      - Form Filling
    humanURL: https://docs.reducto.ai/editing/edit-overview
    properties:
      - url: https://docs.reducto.ai/editing/edit-overview
        type: Documentation
      - url: https://docs.reducto.ai/api-reference/edit
        type: APIReference
      - url: https://docs.reducto.ai/api-reference/edit-async
        type: APIReference
      - url: https://docs.reducto.ai/configs/edit/form-schema
        type: Documentation
      - url: openapi/reducto-edit-api-openapi.yml
        type: OpenAPI
    description: >-
      Fill detected blanks, tables, and checkboxes inside documents from a provided form schema, without requiring
      per-document templates. Beta endpoint priced at 4 credits per page.
  - aid: reducto-ai:reducto-pipeline-api
    name: Reducto Pipeline API
    tags:
      - Document AI
      - Workflow
      - Pipeline
    humanURL: https://docs.reducto.ai/workflows/pipeline-basics
    properties:
      - url: https://docs.reducto.ai/workflows/pipeline-basics
        type: Documentation
      - url: https://docs.reducto.ai/api-reference/pipeline
        type: APIReference
      - url: https://docs.reducto.ai/api-reference/pipeline-async
        type: APIReference
      - url: https://docs.reducto.ai/workflows/multi-document-pipelines
        type: Documentation
      - url: https://docs.reducto.ai/workflows/chaining-endpoints
        type: Documentation
      - url: openapi/reducto-pipeline-api-openapi.yml
        type: OpenAPI
    description: >-
      Compose Parse, Split, Extract, Edit, and Classify into a single multi-step workflow with chained outputs. Supports
      priority requests on Growth, and on-premise / VPC deployments on Enterprise.
  - aid: reducto-ai:reducto-classify-api
    name: Reducto Classify API
    tags:
      - Document AI
      - Classify
      - Document Classification
      - Citations
    humanURL: https://docs.reducto.ai/classify/overview
    properties:
      - url: https://docs.reducto.ai/classify/overview
        type: Documentation
      - url: https://docs.reducto.ai/classify/best-practices
        type: Documentation
      - url: https://docs.reducto.ai/classify/response-format
        type: Documentation
      - url: https://docs.reducto.ai/configs/classify/configuration
        type: Documentation
      - url: openapi/reducto-classify-api-openapi.yml
        type: OpenAPI
    description: >-
      Classify documents into a defined set of categories and run citation lookups against parsed content. Billed at 0.5
      credits per page of context (default 5 pages = 2.5 credits per document).
  - aid: reducto-ai:reducto-jobs-api
    name: Reducto Jobs API
    tags:
      - Document AI
      - Jobs
      - Async
    humanURL: https://docs.reducto.ai/workflows/async-overview
    properties:
      - url: https://docs.reducto.ai/workflows/async-overview
        type: Documentation
      - url: https://docs.reducto.ai/api-reference/get-jobs
        type: APIReference
      - url: https://docs.reducto.ai/api-reference/cancel-job
        type: APIReference
      - url: https://docs.reducto.ai/api-reference/retrieve-parse
        type: APIReference
      - url: openapi/reducto-jobs-api-openapi.yml
        type: OpenAPI
    description: >-
      Retrieve, cancel, and list async jobs created by parse_async, extract_async, split_async, edit_async, and
      pipeline_async. Pairs with direct or Svix-backed webhooks for completion notifications.
  - aid: reducto-ai:reducto-upload-api
    name: Reducto Upload API
    tags:
      - Document AI
      - Upload
      - Storage
    humanURL: https://docs.reducto.ai/upload/overview
    properties:
      - url: https://docs.reducto.ai/upload/overview
        type: Documentation
      - url: https://docs.reducto.ai/upload/large-files
        type: Documentation
      - url: https://docs.reducto.ai/api-reference/upload
        type: APIReference
      - url: openapi/reducto-upload-api-openapi.yml
        type: OpenAPI
    description: >-
      Upload files directly to Reducto storage and receive a reducto://upload reference usable across Parse, Split,
      Extract, Edit, Pipeline, and Classify. Includes large-file (chunked) upload support.
  - aid: reducto-ai:reducto-webhooks-api
    name: Reducto Webhooks API
    tags:
      - Document AI
      - Webhooks
      - Async
    humanURL: https://docs.reducto.ai/workflows/direct-webhooks
    properties:
      - url: https://docs.reducto.ai/workflows/direct-webhooks
        type: Documentation
      - url: https://docs.reducto.ai/workflows/svix-webhooks
        type: Documentation
      - url: https://docs.reducto.ai/api-reference/webhook-portal
        type: Documentation
      - url: https://docs.reducto.ai/api-reference/upload
        type: APIReference
      - url: openapi/reducto-webhooks-api-openapi.yml
        type: OpenAPI
    description: >-
      Configure webhook endpoints for asynchronous job completion. Supports direct webhooks and Svix-backed delivery,
      plus a hosted Webhook Portal for end-customer subscription management.
  - aid: reducto-ai:reducto-platform-api
    name: Reducto Platform API
    tags:
      - Document AI
      - Platform
      - Observability
    humanURL: https://docs.reducto.ai/api-reference/get-version
    properties:
      - url: https://docs.reducto.ai/api-reference/get-version
        type: APIReference
      - url: https://docs.reducto.ai/reference/version-pinning
        type: Documentation
      - url: https://docs.reducto.ai/onprem/observability
        type: Documentation
      - url: openapi/reducto-platform-api-openapi.yml
        type: OpenAPI
    description: >-
      Platform health, version, and metrics endpoints for operating and monitoring Reducto, including Prometheus and
      streaq metrics exposed by on-premise deployments.
common:
  - url: https://reducto.ai
    type: Portal
  - url: https://docs.reducto.ai
    type: Documentation
  - url: https://docs.reducto.ai/overview
    type: Documentation
  - url: https://docs.reducto.ai/quickstart
    type: GettingStarted
  - url: https://docs.reducto.ai/studio-quickstart
    type: GettingStarted
  - url: https://studio.reducto.ai
    type: Console
  - url: https://studio.reducto.ai
    type: SignUp
  - url: https://reducto.ai/pricing
    type: Pricing
  - url: https://reducto.ai/blog
    type: Blog
  - url: https://reducto.ai/contact
    type: Support
  - url: mailto:support@reducto.ai
    type: Support
  - url: https://status.reducto.ai
    type: StatusPage
  - url: https://trust.reducto.ai
    type: TrustCenter
  - url: https://docs.reducto.ai/security/policies
    type: Documentation
  - url: https://docs.reducto.ai/security/eu-data-residency
    type: Documentation
  - url: https://docs.reducto.ai/security/filing-complaints
    type: Documentation
  - url: https://docs.reducto.ai/enterprise/enterprise-readiness
    type: Documentation
  - url: https://reducto.ai/privacy
    type: PrivacyPolicy
  - url: https://reducto.ai/terms
    type: TermsOfService
  - url: https://docs.reducto.ai/reference/rate-limits
    type: RateLimits
  - url: https://docs.reducto.ai/reference/credit-usage
    type: Documentation
  - url: https://docs.reducto.ai/reference/page-billing-breakdown
    type: Documentation
  - url: https://docs.reducto.ai/reference/error-codes
    type: Documentation
  - url: https://docs.reducto.ai/reference/faq
    type: FAQ
  - url: https://docs.reducto.ai/reference/glossary
    type: Glossary
  - url: https://docs.reducto.ai/reference/version-pinning
    type: Documentation
  - url: https://docs.reducto.ai/cli
    name: Reducto CLI
    type: CLI
  - url: https://docs.reducto.ai/mcp-server
    name: Reducto MCP Server
    type: MCP
  - url: https://docs.reducto.ai/agent-guide
    type: Documentation
  - url: https://docs.reducto.ai/openapi.json
    name: OpenAPI (full)
    type: OpenAPI
  - url: https://docs.reducto.ai/openapi-legacy.json
    name: OpenAPI (legacy)
    type: OpenAPI
  - url: https://llms.reducto.ai
    name: LLMs Center
    type: Documentation
  - url: https://docs.reducto.ai/llms.txt
    name: llms.txt
    type: Documentation
  - url: https://docs.reducto.ai/cookbooks/overview
    name: Cookbooks
    type: CodeExamples
  - url: https://docs.reducto.ai/cookbooks/batch-processing
    type: CodeExamples
  - url: https://docs.reducto.ai/cookbooks/financial-analysis
    type: CodeExamples
  - url: https://docs.reducto.ai/cookbooks/form-filling
    type: CodeExamples
  - url: https://docs.reducto.ai/cookbooks/identity-verification
    type: CodeExamples
  - url: https://docs.reducto.ai/cookbooks/invoice-extraction
    type: CodeExamples
  - url: https://docs.reducto.ai/cookbooks/multilingual-processing
    type: CodeExamples
  - url: https://docs.reducto.ai/cookbooks/multimodal-rag-image-results
    type: CodeExamples
  - url: https://docs.reducto.ai/cookbooks/redlined-legal-contracts
    type: CodeExamples
  - url: https://docs.reducto.ai/cookbooks/web-browsing-browserbase
    type: CodeExamples
  - url: https://docs.reducto.ai/onprem/enterprise_deployment_options
    type: Documentation
  - url: https://docs.reducto.ai/onprem/hybrid-vpc-deployment
    type: Documentation
  - url: https://docs.reducto.ai/onprem/hybrid-vpc-aws
    type: Documentation
  - url: https://docs.reducto.ai/onprem/hybrid-vpc-azure
    type: Documentation
  - url: https://docs.reducto.ai/onprem/hybrid-vpc-gcs
    type: Documentation
  - url: https://docs.reducto.ai/onprem/hybrid-vpc-box
    type: Documentation
  - url: https://docs.reducto.ai/onprem/security_model
    type: Documentation
  - url: https://docs.reducto.ai/onprem/changelog
    type: ChangeLog
  - url: plans/reducto-plans-pricing.yml
    type: Plans
  - url: rate-limits/reducto-rate-limits.yml
    type: RateLimits
  - url: finops/reducto-finops.yml
    type: FinOps
  - type: Features
    data:
      - >-
        Parse — agentic OCR with error correction, layout-aware extraction across 30+ file types (PDFs, images,
        spreadsheets, slides, Office docs, text)
      - >-
        Extract — schema-driven structured data extraction with Deep Extract, Array Extract, and Citations that pin
        fields to source page + bounding box
      - Split — automatic separation of multi-document files and long forms via rules-based Split or Deep Split
      - Edit — template-free form filling for blanks, tables, and checkboxes from a form schema (beta)
      - Classify — page-context document classification with optional citations
      - Pipeline — single-call composition of Parse + Split + Extract + Edit + Classify with chained outputs
      - Cite — citation lookup endpoint surfacing source-level references inside parsed content
      - >-
        Async endpoints (parse_async, extract_async, split_async, edit_async, pipeline_async) plus a Jobs API for
        retrieve, cancel, and list
      - Direct webhooks and Svix-backed webhooks for async completion, with a hosted Webhook Portal
      - Upload API with large-file chunked uploads producing reducto:// references reusable across endpoints
      - jobid:// references that let Extract / Split / Edit reuse a prior Parse without re-billing
      - Multilingual parsing across 100+ languages with automatic page rotation
      - Intelligent chunking (variable, section, page, block) optimized for LLM/embedding pipelines
      - Figure summarization, chart extraction, equation handling, list detection, and discardable-block tagging
      - Spreadsheet parsing with table splitting, cell colors, formulas, and clustering modes
      - Table output formats — HTML, JSON, Markdown, CSV, and AI-JSON
      - Studio — visual workbench for Parse, Split, Extract, Edit, and Pipeline deployment
      - Studio Deploy Pipeline — push designed workflows directly to production
      - Official SDKs in Python, Node.js, and Go plus a Reducto CLI
      - Reducto MCP Server for agent integration
      - LLMs Center (llms.reducto.ai) and llms.txt for AI-agent friendly documentation
      - >-
        Hybrid VPC and on-premise deployment options (AWS, Azure, GCS, Box) with database, OCR, LLM, fair-queueing,
        observability, and file-cleanup configuration
      - EU data residency endpoints on Growth+
      - Zero-data-retention option and Business Associate Agreement on Growth+
      - >-
        Token-style rate limits — 200 concurrent sync requests, 500 RPS submission; tiered per-second sync rate (1 RPS
        Standard, 10 RPS Growth, 100+ RPS Enterprise)
      - >-
        Credit-based pricing — Parse 1-4 credits/page, Extract 2 credits/page (Deep Extract 4 + 0.1/field, min 30),
        Split 2-4 credits/page, Edit 4 credits/page, Classify 0.5 credits/page-of-context
      - 15,000 free credits on the Standard plan, then $0.015 per credit
    sources:
      - https://reducto.ai
      - https://docs.reducto.ai/overview
      - https://docs.reducto.ai/reference/credit-usage
      - https://docs.reducto.ai/reference/rate-limits
      - https://reducto.ai/pricing
    updated: '2026-05-25'
  - type: UseCases
    data:
      - name: Financial document analysis
        description: >-
          Parse 10-Ks, prospectuses, KBYC packets, broker statements, and credit memos to extract tables, line items,
          and structured financials for downstream analytics or LLM agents.
      - name: Insurance claims and underwriting
        description: >-
          Split multi-document claim packets, classify each unit (police report, medical record, photo, ACORD form), and
          extract structured fields with citations for adjuster review.
      - name: Healthcare records processing
        description: >-
          Extract structured patient, encounter, lab, and medication data from scanned EOBs, charts, and faxes under a
          BAA with zero data retention.
      - name: Legal contract review
        description: >-
          Surface redlined clauses, defined terms, and obligation language from redlined contracts and case files with
          field-level citations back to the source page.
      - name: Government and public-sector forms
        description: >-
          Fill, extract, and classify long-form government applications, permits, and disclosure filings using the Edit
          and Pipeline APIs.
      - name: Logistics, supply chain, and trade
        description: >-
          Parse invoices, BOLs, customs forms, certificates of origin, and packing lists in bulk to feed ERP and TMS
          systems.
      - name: Identity verification
        description: >-
          Extract and validate fields from passports, IDs, and proof-of-address documents using the Identity
          Verification cookbook.
      - name: Invoice and AP automation
        description: >-
          Capture vendor, line-item, and tax data from invoices with citations to source bounding boxes for review and
          approval.
      - name: Multilingual document processing
        description: Parse and extract from documents in 100+ languages with consistent schemas.
      - name: Multimodal RAG ingestion
        description: >-
          Produce LLM-optimized chunks (with figure summarization, embed strings, and bounding boxes) ready for vector
          indexing.
    sources:
      - https://reducto.ai
      - https://docs.reducto.ai/cookbooks/overview
    updated: '2026-05-25'
  - type: Integrations
    data:
      - name: AWS S3 / Hybrid VPC on AWS
        description: Presigned S3 URLs as parse inputs, plus hybrid VPC deployment on AWS for on-prem-grade isolation.
      - name: Azure / Hybrid VPC on Azure
        description: Hybrid VPC deployment on Azure for regulated workloads.
      - name: Google Cloud / Hybrid VPC on GCS
        description: Hybrid VPC deployment on GCS for regulated workloads.
      - name: Box / Hybrid VPC on Box
        description: Pull documents from Box for parsing in a hybrid VPC topology.
      - name: Browserbase
        description: Web-browsing cookbook that pairs Browserbase with Reducto for live web-document capture.
      - name: Svix
        description: Webhook delivery and management via Svix-backed webhook portals.
      - name: Model Context Protocol (MCP)
        description: Reducto MCP Server exposes Parse / Extract / Split / Edit / Classify as MCP tools to AI agents.
      - name: OpenAPI tooling
        description: Public OpenAPI 3.1 spec at docs.reducto.ai/openapi.json plus a legacy spec for backwards compatibility.
    sources:
      - https://docs.reducto.ai
      - https://docs.reducto.ai/onprem/enterprise_deployment_options
    updated: '2026-05-25'
  - type: Solutions
    data:
      - name: Standard
        description: Pay-as-you-go credit plan, 15,000 free credits, then $0.015/credit; 1 RPS sync; up to 5 Studio seats.
      - name: Growth
        description: >-
          Volume-discounted plan adding zero-data-retention, BAA, 10 RPS sync, up to 5 active priority requests, EU data
          residency, priority support, and unlimited Studio seats.
      - name: Enterprise
        description: >-
          Adds VPC and on-premises deployment, custom MSA/SLA, dedicated support, RBAC, SSO/SAML, and 100+ RPS custom
          throughput.
    sources:
      - https://reducto.ai/pricing
    updated: '2026-05-25'
created: '2026-05-25'
modified: '2026-05-25'
position: Consuming
description: >-
  Reducto is an AI document-parsing platform that turns unstructured PDFs, images, spreadsheets, slides, and forms into
  LLM-ready layout, structured data, and form completions. The API exposes Parse, Extract, Split, Edit, Classify, and
  Pipeline endpoints — each with sync and async variants — plus an Upload API, Webhooks API, and Jobs API. Used by Scale
  AI, Vanta, Harvey, Medallion, Toast, JLL, Vise, Newfront, and Legora to power document AI in finance, healthcare,
  insurance, legal, government, and logistics.
maintainers:
  - FN: Kin Lane
    email: info@apievangelist.com
    X: apievangelist
    url: https://apievangelist.com