Chunkr

Chunkr is an open-source document intelligence platform that turns complex documents (PDF, Office, images) into RAG- and LLM-ready data. The Chunkr Cloud API at api.chunkr.ai performs layout analysis, OCR, segmentation, and chunking, and runs proprietary in-house vision models; the AGPL-3.0 open-source release (lumina-ai-inc/chunkr) can be self-hosted via Docker.

5 APIs 0 Features

Document ParsingOCRChunkingRAGDocument Intelligence

APIs

Chunkr Parse Task API

Creates a parse task that runs layout analysis, OCR, segmentation, and chunking over an uploaded document, returning structured chunks, pages, and segment metadata with configur...

Chunkr Extract Task API

Creates an extract task that pulls schema-driven structured data from a document, returning JSON output with citations and metrics against a caller-supplied extraction schema an...

Chunkr Task Management API

Retrieves, lists, cancels, and deletes parse and extract tasks - get a task by id, get its parse or extract output, list tasks with pagination, cancel a running task, and delete...

Chunkr Files API

Uploads, lists, retrieves, downloads, and deletes files that can be referenced by parse and extract tasks via ch://files/{file_id} references.

Chunkr Health and Extras API

Liveness health check and metadata helpers, including listing all supported file types accepted by the parsing and extraction pipelines.

Collections

Chunkr API

OPEN

Pricing Plans

Chunkr Ai Plans Pricing

6 plans

PLANS

Rate Limits

Chunkr Ai Rate Limits

4 limits

RATE LIMITS

FinOps

Chunkr Ai Finops

FINOPS

Resources

👥

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: Chunkr API
  version: '1.0'
request:
  auth:
    type: apikey
    key: Authorization
    value: '{{apiKey}}'
    in: header
items:
- info:
    name: Tasks
    type: folder
  items:
  - info:
      name: Create a parse task.
      type: http
    http:
      method: POST
      url: https://api.chunkr.ai/tasks/parse
      body:
        type: json
        data: "{\n  \"file\": \"https://example.com/document.pdf\",\n  \"chunk_processing\": { \"target_length\": 4096, \"\
          tokenizer\": \"Word\" },\n  \"ocr_strategy\": \"All\",\n  \"segmentation_strategy\": \"LayoutAnalysis\",\n  \"error_handling\"\
          : \"Fail\"\n}"
    docs: Runs layout analysis, OCR, segmentation, and chunking over a document.
  - info:
      name: Create an extract task.
      type: http
    http:
      method: POST
      url: https://api.chunkr.ai/tasks/extract
      body:
        type: json
        data: "{\n  \"file\": \"https://example.com/invoice.pdf\",\n  \"schema\": { \"invoice_number\": \"string\", \"total\"\
          : \"number\" }\n}"
    docs: Pulls schema-driven structured data from a document.
  - info:
      name: List tasks.
      type: http
    http:
      method: GET
      url: https://api.chunkr.ai/tasks?page=1&limit=10
    docs: Returns a paginated list of tasks.
  - info:
      name: Get a task.
      type: http
    http:
      method: GET
      url: https://api.chunkr.ai/tasks/{{task_id}}?include_chunks=true
    docs: Retrieves a parse or extract task by id, including output when completed.
  - info:
      name: Get a parse task.
      type: http
    http:
      method: GET
      url: https://api.chunkr.ai/tasks/{{task_id}}/parse
    docs: Retrieves the parse-specific output for a task.
  - info:
      name: Get an extract task.
      type: http
    http:
      method: GET
      url: https://api.chunkr.ai/tasks/{{task_id}}/extract
    docs: Retrieves the extract-specific output for a task.
  - info:
      name: Cancel a task.
      type: http
    http:
      method: POST
      url: https://api.chunkr.ai/tasks/{{task_id}}/cancel
    docs: Cancels a task that is queued or processing.
  - info:
      name: Delete a task.
      type: http
    http:
      method: DELETE
      url: https://api.chunkr.ai/tasks/{{task_id}}
    docs: Deletes a task and its associated artifacts.
- info:
    name: Files
    type: folder
  items:
  - info:
      name: Upload a file.
      type: http
    http:
      method: POST
      url: https://api.chunkr.ai/files
      body:
        type: multipart-form
        data: []
    docs: Uploads a file that can be referenced from a parse or extract task.
  - info:
      name: List files.
      type: http
    http:
      method: GET
      url: https://api.chunkr.ai/files
    docs: Returns a paginated list of uploaded files.
  - info:
      name: Get a file.
      type: http
    http:
      method: GET
      url: https://api.chunkr.ai/files/{{file_id}}
    docs: Retrieves a file record.
  - info:
      name: Download file content.
      type: http
    http:
      method: GET
      url: https://api.chunkr.ai/files/{{file_id}}/download
    docs: Downloads the raw file content.
  - info:
      name: Get a file URL.
      type: http
    http:
      method: GET
      url: https://api.chunkr.ai/files/{{file_id}}/url
    docs: Returns a presigned URL for the stored file.
  - info:
      name: Delete a file.
      type: http
    http:
      method: DELETE
      url: https://api.chunkr.ai/files/{{file_id}}
    docs: Deletes a file.
- info:
    name: Health
    type: folder
  items:
  - info:
      name: Health check.
      type: http
    http:
      method: GET
      url: https://api.chunkr.ai/health
    docs: Liveness check for the Chunkr API.
  - info:
      name: Get all supported file types.
      type: http
    http:
      method: GET
      url: https://api.chunkr.ai/extras/supported-file-types
    docs: Lists the file types accepted by the parsing and extraction pipelines.
bundled: true