Unstructured

aid: unstructured
name: Unstructured
description: >-
  Unstructured is a document parsing and pre-processing platform that provides
  a REST API for ingesting PDFs, HTML, DOCX, images, and more than 50 other
  file formats, transforming them into clean structured JSON chunks ready for
  RAG pipelines and LLM applications. The platform offers partitioning,
  enrichment, chunking, and embedding capabilities via both a SaaS serverless
  API and self-hosted deployments. Billing is calculated on a per-page basis,
  with a free tier of 15,000 pages, pay-as-you-go at $0.03 per page, and
  custom enterprise pricing. Unstructured also ships Python and JavaScript SDKs,
  an MCP server for AI agent workflows, and 40+ connectors for source and
  destination data systems including S3, Databricks, and vector databases.
type: Index
image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
tags:
  - document-processing
  - ETL
  - RAG
  - LLM
  - PDF
  - OCR
  - data-ingestion
  - chunking
  - embeddings
  - AI
url: https://raw.githubusercontent.com/api-evangelist/unstructured/refs/heads/main/apis.yml
created: '2026-06-12'
modified: '2026-06-12'
specificationVersion: '0.19'
apis:
  - aid: unstructured-platform-api
    name: Unstructured Platform API
    description: >-
      The Unstructured Platform API provides programmatic access to workflow
      operations including source connectors, destination connectors, workflows,
      and jobs. It enables headless, push-style data transformation pipelines
      that partition, enrich, chunk, and embed documents from 50+ file formats
      into AI-ready JSON output suitable for RAG and LLM applications.
    humanURL: https://docs.unstructured.io/api-reference/overview
    baseURL: https://platform.unstructuredapp.io/api/v1
    tags:
      - document-processing
      - workflows
      - connectors
      - RAG
      - ETL
    properties:
      - type: Documentation
        url: https://docs.unstructured.io/api-reference/overview
      - type: OpenAPI
        url: https://raw.githubusercontent.com/api-evangelist/unstructured/refs/heads/main/openapi/unstructured-platform-api-openapi.yml
  - aid: unstructured-partition-endpoint
    name: Unstructured Partition Endpoint
    description: >-
      The Unstructured Partition Endpoint is the legacy serverless API for
      processing individual files on demand. It supports PDFs, images, DOCX,
      HTML, and dozens of other formats, returning structured element JSON with
      configurable processing strategies including fast, hi_res, ocr_only, and
      auto. Authentication uses API key headers.
    humanURL: https://docs.unstructured.io/api-reference/api-services/saas-api-development-guide
    baseURL: https://api.unstructured.io/general/v0/general
    tags:
      - document-partitioning
      - OCR
      - PDF
      - serverless
    properties:
      - type: Documentation
        url: https://docs.unstructured.io/api-reference/api-services/saas-api-development-guide
      - type: PythonSDK
        url: https://github.com/Unstructured-IO/unstructured-python-client
      - type: JavaScriptSDK
        url: https://github.com/Unstructured-IO/unstructured-js-client
      - type: OpenAPI
        url: https://raw.githubusercontent.com/api-evangelist/unstructured/refs/heads/main/openapi/unstructured-partition-endpoint-openapi.yml
common:
  - type: Website
    url: https://unstructured.io
  - type: Documentation
    url: https://docs.unstructured.io
  - type: GitHubOrganization
    url: https://github.com/Unstructured-IO
  - type: LinkedIn
    url: https://www.linkedin.com/company/unstructuredio/
  - type: X
    url: https://twitter.com/UnstructuredIO
  - type: Blog
    url: https://unstructured.io/blog
  - type: Pricing
    url: https://unstructured.io/pricing
  - type: StatusPage
    url: https://unstructuredio.trust.pagerduty.com/posts/dashboard
  - type: PythonSDK
    url: https://github.com/Unstructured-IO/unstructured-python-client
  - type: JavaScriptSDK
    url: https://github.com/Unstructured-IO/unstructured-js-client
  - type: MCPServer
    url: https://github.com/Unstructured-IO/UNS-MCP
  - type: Plans
    url: plans/unstructured-plans-pricing.yml
  - type: RateLimits
    url: rate-limits/unstructured-rate-limits.yml
  - type: FinOps
    url: finops/unstructured-finops.yml
  - type: Vocabulary
    url: https://raw.githubusercontent.com/api-evangelist/unstructured/refs/heads/main/vocabulary/unstructured-vocabulary.yml
  - type: JSONSchema
    url: https://raw.githubusercontent.com/api-evangelist/unstructured/refs/heads/main/json-schema/unstructured-schemas.json
  - type: JSONLDContext
    url: https://raw.githubusercontent.com/api-evangelist/unstructured/refs/heads/main/json-ld/unstructured-context.jsonld
maintainers:
  - FN: Kin Lane
    email: [email protected]