Skip to main content
POST
/
parse
Parse
import requests

url = "https://platform.reducto.ai/parse"

payload = {
    "document_url": "<string>",
    "options": {
        "ocr_mode": "standard",
        "extraction_mode": "ocr",
        "chunking": {
            "chunk_mode": "variable",
            "chunk_overlap": 0
        },
        "table_summary": { "enabled": False },
        "figure_summary": {
            "enabled": False,
            "prompt": "<string>",
            "override": False,
            "advanced_chart_agent": False
        },
        "filter_blocks": [],
        "force_url_result": False
    },
    "advanced_options": {
        "ocr_system": "highres",
        "table_output_format": "html",
        "merge_tables": False,
        "include_formula_information": False,
        "include_color_information": False,
        "include_dropdown_information": False,
        "continue_hierarchy": True,
        "keep_line_breaks": False,
        "page_range": {},
        "force_file_extension": "<string>",
        "large_table_chunking": {
            "enabled": True,
            "size": 50
        },
        "spreadsheet_table_clustering": "default",
        "max_cell_count": 2,
        "add_page_markers": False,
        "remove_text_formatting": False,
        "return_ocr_data": False,
        "document_password": "<string>",
        "filter_line_numbers": False,
        "read_comments": False,
        "persist_results": False,
        "exclude_hidden_sheets": False,
        "exclude_hidden_rows_cols": False,
        "enable_change_tracking": False,
        "enable_highlight_detection": False,
        "ignore_watermarks": False
    },
    "experimental_options": {
        "enrich": {
            "enabled": False,
            "mode": "standard"
        },
        "layout_enrichment": False,
        "enable_checkboxes": False,
        "enable_equations": False,
        "rotate_pages": True,
        "rotate_figures": False,
        "enable_scripts": False,
        "return_figure_images": False,
        "return_table_images": False,
        "return_page_images": False,
        "layout_model": "default",
        "embed_text_metadata_pdf": False,
        "embed_pdf_metadata_dpi": 100,
        "detect_signatures": False,
        "danger_filter_wide_boxes": False,
        "user_specified_timeout_seconds": 123
    },
    "priority": True
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    document_url: '<string>',
    options: {
      ocr_mode: 'standard',
      extraction_mode: 'ocr',
      chunking: {chunk_mode: 'variable', chunk_overlap: 0},
      table_summary: {enabled: false},
      figure_summary: {
        enabled: false,
        prompt: '<string>',
        override: false,
        advanced_chart_agent: false
      },
      filter_blocks: [],
      force_url_result: false
    },
    advanced_options: {
      ocr_system: 'highres',
      table_output_format: 'html',
      merge_tables: false,
      include_formula_information: false,
      include_color_information: false,
      include_dropdown_information: false,
      continue_hierarchy: true,
      keep_line_breaks: false,
      page_range: {},
      force_file_extension: '<string>',
      large_table_chunking: {enabled: true, size: 50},
      spreadsheet_table_clustering: 'default',
      max_cell_count: 2,
      add_page_markers: false,
      remove_text_formatting: false,
      return_ocr_data: false,
      document_password: '<string>',
      filter_line_numbers: false,
      read_comments: false,
      persist_results: false,
      exclude_hidden_sheets: false,
      exclude_hidden_rows_cols: false,
      enable_change_tracking: false,
      enable_highlight_detection: false,
      ignore_watermarks: false
    },
    experimental_options: {
      enrich: {enabled: false, mode: 'standard'},
      layout_enrichment: false,
      enable_checkboxes: false,
      enable_equations: false,
      rotate_pages: true,
      rotate_figures: false,
      enable_scripts: false,
      return_figure_images: false,
      return_table_images: false,
      return_page_images: false,
      layout_model: 'default',
      embed_text_metadata_pdf: false,
      embed_pdf_metadata_dpi: 100,
      detect_signatures: false,
      danger_filter_wide_boxes: false,
      user_specified_timeout_seconds: 123
    },
    priority: true
  })
};

fetch('https://platform.reducto.ai/parse', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://platform.reducto.ai/parse"

	payload := strings.NewReader("{\n  \"document_url\": \"<string>\",\n  \"options\": {\n    \"ocr_mode\": \"standard\",\n    \"extraction_mode\": \"ocr\",\n    \"chunking\": {\n      \"chunk_mode\": \"variable\",\n      \"chunk_overlap\": 0\n    },\n    \"table_summary\": {\n      \"enabled\": false\n    },\n    \"figure_summary\": {\n      \"enabled\": false,\n      \"prompt\": \"<string>\",\n      \"override\": false,\n      \"advanced_chart_agent\": false\n    },\n    \"filter_blocks\": [],\n    \"force_url_result\": false\n  },\n  \"advanced_options\": {\n    \"ocr_system\": \"highres\",\n    \"table_output_format\": \"html\",\n    \"merge_tables\": false,\n    \"include_formula_information\": false,\n    \"include_color_information\": false,\n    \"include_dropdown_information\": false,\n    \"continue_hierarchy\": true,\n    \"keep_line_breaks\": false,\n    \"page_range\": {},\n    \"force_file_extension\": \"<string>\",\n    \"large_table_chunking\": {\n      \"enabled\": true,\n      \"size\": 50\n    },\n    \"spreadsheet_table_clustering\": \"default\",\n    \"max_cell_count\": 2,\n    \"add_page_markers\": false,\n    \"remove_text_formatting\": false,\n    \"return_ocr_data\": false,\n    \"document_password\": \"<string>\",\n    \"filter_line_numbers\": false,\n    \"read_comments\": false,\n    \"persist_results\": false,\n    \"exclude_hidden_sheets\": false,\n    \"exclude_hidden_rows_cols\": false,\n    \"enable_change_tracking\": false,\n    \"enable_highlight_detection\": false,\n    \"ignore_watermarks\": false\n  },\n  \"experimental_options\": {\n    \"enrich\": {\n      \"enabled\": false,\n      \"mode\": \"standard\"\n    },\n    \"layout_enrichment\": false,\n    \"enable_checkboxes\": false,\n    \"enable_equations\": false,\n    \"rotate_pages\": true,\n    \"rotate_figures\": false,\n    \"enable_scripts\": false,\n    \"return_figure_images\": false,\n    \"return_table_images\": false,\n    \"return_page_images\": false,\n    \"layout_model\": \"default\",\n    \"embed_text_metadata_pdf\": false,\n    \"embed_pdf_metadata_dpi\": 100,\n    \"detect_signatures\": false,\n    \"danger_filter_wide_boxes\": false,\n    \"user_specified_timeout_seconds\": 123\n  },\n  \"priority\": true\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}
{
  "job_id": "<string>",
  "duration": 123,
  "usage": {
    "num_pages": 123,
    "credits": 123,
    "credit_breakdown": {},
    "page_billing_breakdown": {},
    "non_empty_cell_count": 123
  },
  "result": {
    "type": "<string>",
    "chunks": [
      {
        "content": "<string>",
        "embed": "<string>",
        "enriched": "<string>",
        "blocks": [
          {}
        ],
        "enrichment_success": false
      }
    ],
    "ocr": {
      "words": [
        {
          "text": "<string>",
          "bbox": {
            "left": 123,
            "top": 123,
            "width": 123,
            "height": 123,
            "page": 123,
            "original_page": 123
          },
          "confidence": 123,
          "chunk_index": 123,
          "rotation": 123
        }
      ],
      "lines": [
        {
          "text": "<string>",
          "bbox": {
            "left": 123,
            "top": 123,
            "width": 123,
            "height": 123,
            "page": 123,
            "original_page": 123
          },
          "confidence": 123,
          "chunk_index": 123,
          "rotation": 123
        }
      ]
    },
    "custom": null
  },
  "response_type": "parse",
  "pdf_url": "<string>",
  "studio_link": "<string>"
}
{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
document_url
required

The URL of the document to be processed. You can provide one of the following:

  1. A publicly available URL
  2. A presigned S3 URL
  3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document
​
options
BaseProcessingOptions · object
​
advanced_options
AdvancedProcessingOptions · object
​
experimental_options
ExperimentalProcessingOptions · object
​
priority
boolean
default:true

If True, attempts to process the job with priority if the user has priority processing budget available; by default, sync jobs are prioritized above async jobs.

Response

Successful Response

​
job_id
string
required
​
duration
number
required

The duration of the parse request in seconds.

​
usage
ParseUsage · object
required
​
result
FullResult · object
required

The response from the document processing service. Note that there can be two types of responses, Full Result and URL Result. This is due to limitations on the max return size on HTTPS. If the response is too large, it will be returned as a presigned URL in the URL response. You should handle this in your application.

​
response_type
string
default:parse
Allowed value: "parse"
​
pdf_url
string | null

The storage URL of the converted PDF file.

​
studio_link
string | null

The link to the studio pipeline for the document.

​
parse_mode
enum<string> | null

Which pipeline produced this response. lite means Reducto Flash Lite served the request; base is the standard pipeline. Optional / nullable for forward compatibility — older API instances or persisted responses written before this field existed will leave it None; treat None as base.

Available options:
base,
lite