Maton

Reducto

Access the Reducto document processing API with managed API key authentication. Parse documents, extract structured data, split documents into sections, and edit PDFs/DOCX files.

Reference

Synchronous Parse

POST /reducto/parse
Content-Type: application/json

{
  "document_url": "https://example.com/document.pdf"
}

Response:

{
  "job_id": "04b8aa38-7eb3-4151-98b0-dbaea71358d9",
  "duration": 17.85,
  "pdf_url": "https://...",
  "studio_link": "https://studio.reducto.ai/job/...",
  "usage": {
    "num_pages": 15,
    "credits": 15.0
  },
  "result": {
    "chunks": [
      {
        "content": "Extracted text content...",
        "blocks": [...]
      }
    ]
  }
}

Asynchronous Parse

For long documents, use async to avoid timeouts:

POST /reducto/parse_async
Content-Type: application/json

{
  "document_url": "https://example.com/document.pdf"
}

Response:

{
  "job_id": "e234ba95-410a-4dd0-8a14-743dbfc49470"
}

Poll the job status with GET /reducto/job/{job_id}.

Synchronous Extract

POST /reducto/extract
Content-Type: application/json

{
  "document_url": "https://example.com/document.pdf",
  "schema": {
    "type": "object",
    "properties": {
      "title": {"type": "string", "description": "The document title"},
      "authors": {"type": "array", "items": {"type": "string"}, "description": "List of author names"}
    }
  }
}

Response:

{
  "job_id": "36f01a34-7ef6-40da-9e74-7c14902b6182",
  "usage": {
    "num_pages": 15,
    "num_fields": 9,
    "credits": 45.0
  },
  "studio_link": "https://studio.reducto.ai/job/...",
  "result": [
    {
      "title": "Document Title",
      "authors": ["Author One", "Author Two"]
    }
  ]
}

Asynchronous Extract

POST /reducto/extract_async
Content-Type: application/json

{
  "document_url": "https://example.com/document.pdf",
  "schema": {
    "type": "object",
    "properties": {
      "title": {"type": "string"}
    }
  }
}

Response:

{
  "job_id": "0cdb6a50-df92-438b-875b-8b5c72d5b089"
}

Synchronous Split

POST /reducto/split
Content-Type: application/json

{
  "document_url": "https://example.com/document.pdf",
  "split_description": [
    {"name": "abstract", "description": "The abstract section"},
    {"name": "introduction", "description": "The introduction section"},
    {"name": "conclusion", "description": "The conclusion section"}
  ]
}

Response:

{
  "usage": {
    "num_pages": 15,
    "credits": 15.0
  },
  "result": {
    "section_mapping": {
      "abstract": [1],
      "introduction": [1, 2],
      "conclusion": [14, 15]
    },
    "splits": [
      {
        "name": "abstract",
        "pages": [1],
        "conf": "high"
      }
    ]
  }
}

Asynchronous Split

POST /reducto/split_async
Content-Type: application/json

{
  "document_url": "https://example.com/document.pdf",
  "split_description": [
    {"name": "abstract", "description": "The abstract section"}
  ]
}

Response:

{
  "job_id": "381de5fe-e162-4039-9ef9-8522fb34056b"
}

Synchronous Edit

POST /reducto/edit
Content-Type: application/json

{
  "document_url": "https://example.com/form.pdf",
  "edit_instructions": "Fill in the name field with 'John Doe' and check the consent box"
}

Response:

{
  "document_url": "https://presigned-url.s3.amazonaws.com/...",
  "form_schema": [...],
  "usage": {
    "num_pages": 2,
    "credits": 2.0
  }
}

Asynchronous Edit

POST /reducto/edit_async
Content-Type: application/json

{
  "document_url": "https://example.com/form.pdf",
  "edit_instructions": "Highlight all mentions of 'important' in red"
}

Response:

{
  "job_id": "575189cb-8732-429a-ba8a-06de8ee03208"
}

Upload File

Upload a document to Reducto and get a presigned URL for processing.

POST /reducto/upload
Content-Type: application/json

{}

Response:

{
  "file_id": "reducto://18d574c7-4144-4f50-b7af-b8aba83ada5d",
  "presigned_url": "https://prod-storage.s3.amazonaws.com/...?AWSAccessKeyId=...&Signature=...&Expires=..."
}

Upload your file to the presigned_url using a PUT request, then use the file_id as document_url in parse/extract/split/edit requests.

Pipeline

Execute pre-configured processing pipelines.

POST /reducto/pipeline
Content-Type: application/json

{
  "input": "https://example.com/document.pdf",
  "pipeline_id": "your-pipeline-id"
}

Note: pipeline_id must be a valid pipeline ID configured in your Reducto account via the Reducto Studio.

Response:

{
  "job_id": "...",
  "usage": {
    "num_pages": 15,
    "credits": 15.0
  },
  "result": {
    "parse": {...},
    "extract": {...},
    "split": {...},
    "edit": {...}
  }
}

List Jobs

GET /reducto/jobs

Response:

{
  "jobs": [
    {
      "job_id": "8c25561f-247a-4843-b561-1eb94c3792d1",
      "status": "Completed",
      "type": "Parse",
      "created_at": "2026-02-27T23:11:39.787917",
      "num_pages": 15,
      "duration": 6.62
    }
  ],
  "next_cursor": null
}

Get Job Status

GET /reducto/job/{job_id}

Response (Pending):

{
  "status": "Pending",
  "result": null,
  "progress": 0.5,
  "reason": null
}

Response (Completed):

{
  "status": "Completed",
  "result": {
    "job_id": "...",
    "duration": 17.85,
    "usage": {...},
    "result": {...}
  },
  "progress": null,
  "reason": null
}

Job status values: Pending, InProgress, Completed, Failed

Version

GET /reducto/version

Response:

"VERSION_GOES_HERE"

Resources

PreviousQuoNextResend

On this page

Reference
Synchronous Parse
Asynchronous Parse
Synchronous Extract
Asynchronous Extract
Synchronous Split
Asynchronous Split
Synchronous Edit
Asynchronous Edit
Upload File
Pipeline
List Jobs
Get Job Status
Version
Resources