Download extraction result
curl --request GET \
--url https://api.runpulse.com/results/{jobId} \
--header 'x-api-key: <api-key>'import requests
url = "https://api.runpulse.com/results/{jobId}"
headers = {"x-api-key": "<api-key>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {'x-api-key': '<api-key>'}};
fetch('https://api.runpulse.com/results/{jobId}', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.runpulse.com/results/{jobId}",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
CURLOPT_HTTPHEADER => [
"x-api-key: <api-key>"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://api.runpulse.com/results/{jobId}"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("x-api-key", "<api-key>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://api.runpulse.com/results/{jobId}")
.header("x-api-key", "<api-key>")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.runpulse.com/results/{jobId}")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["x-api-key"] = '<api-key>'
response = http.request(request)
puts response.read_body{
"markdown": "<string>",
"extensions": {
"document_metadata": {
"file": {
"name": "<string>",
"extension": "<string>",
"media_type": "<string>",
"size_bytes": 1,
"sha256": "<string>"
},
"properties": {
"title": "<string>",
"authors": [
"<string>"
],
"subject": "<string>",
"description": "<string>",
"keywords": [
"<string>"
],
"language": "<string>",
"application": "<string>",
"application_version": "<string>",
"producer": "<string>",
"last_modified_by": "<string>",
"revision": "<string>",
"category": "<string>",
"content_status": "<string>",
"identifier": "<string>",
"version": "<string>",
"company": "<string>",
"manager": "<string>",
"template": "<string>",
"presentation_format": "<string>",
"editing_time_minutes": 1,
"copyright": "<string>",
"created_at": "<string>",
"modified_at": "<string>"
},
"structure": {
"page_count": 1,
"page_labels": [
"<string>"
],
"page_sizes": [
{}
],
"outline_count": 1,
"attachment_count": 1,
"annotation_count": 1,
"annotation_types": {},
"form_field_count": 1,
"sheet_count": 1,
"sheet_names": [
"<string>"
],
"sheet_visibility": {},
"active_sheet": "<string>",
"slide_count": 1,
"note_count": 1,
"hidden_slide_count": 1,
"multimedia_clip_count": 1,
"word_count": 1,
"character_count": 1,
"character_count_with_spaces": 1,
"line_count": 1,
"paragraph_count": 1,
"paragraph_count_derived": 1,
"table_count": 1,
"section_count": 1,
"embedded_image_count": 1,
"width_px": 1,
"height_px": 1,
"frame_count": 1,
"row_count": 1,
"max_column_count": 1
},
"warnings": [
"<string>"
],
"custom": {},
"format_specific": {}
},
"chunking": {
"semantic": [
"<string>"
],
"header": [
"<string>"
],
"page": [
"<string>"
],
"recursive": [
"<string>"
]
},
"footnoteReferences": [
{
"symbol": "<string>",
"footnoteTextId": "<string>",
"footnotePageNumber": 2,
"footnoteText": "<string>",
"referenceTextIds": [
"<string>"
],
"references": [
{
"textId": "<string>",
"tableId": "<string>",
"row": 123,
"column": 123,
"pageNumber": 2,
"markerBoundingBox": [
123
],
"source": "native"
}
]
}
],
"altOutputs": {
"wlbb": {
"words": [
{
"id": "<string>",
"text": "<string>",
"page_number": 2,
"bounding_box": [
123
],
"average_word_confidence": 123
}
],
"error": "<string>"
},
"html": "<string>",
"xml": "<string>"
}
},
"bounding_boxes": {
"Images": [
{
"id": "<string>",
"visual_type": "chart",
"content": "<string>",
"caption": "<string>",
"page_number": 2,
"confidence": 123,
"bounding_box": [
123
],
"image_url": "<string>",
"description": "<string>",
"classification": {
"confidence": 0.5,
"model": "<string>",
"error": "<string>"
},
"sheet_name": "<string>",
"sheet_index": 123,
"workbook_sheet_index": 123,
"excel_range": "<string>",
"chart_type": "<string>",
"chart_title": "<string>",
"source_ranges": [
"<string>"
],
"render_error": "<string>",
"description_error": "<string>"
}
],
"Tables": [
{
"table_info": {
"id": "<string>",
"dimensions": [
123
],
"excel_range": "<string>",
"sheet_name": "<string>",
"sheet_index": 123,
"workbook_sheet_index": 123,
"section_index": 123,
"section_type": "<string>",
"section_name": "<string>",
"table_name": "<string>",
"layout_type": "<string>",
"is_chart": true,
"chart_type": "<string>",
"chart_title": "<string>",
"source_ranges": [
"<string>"
],
"location": {},
"confidence": 0.5
},
"confidence": 0.5,
"cell_data": [
{
"confidence": 0.5
}
]
}
],
"Text": [
{
"id": "<string>",
"content": "<string>",
"page_number": 2,
"confidence": 0.5,
"reading_order": 1,
"bounding_box": [
123
],
"excel_range": "<string>",
"sheet_name": "<string>",
"sheet_index": 123,
"workbook_sheet_index": 123,
"selected": true
}
],
"Title": [
{
"id": "<string>",
"content": "<string>",
"page_number": 2,
"confidence": 0.5,
"reading_order": 1,
"bounding_box": [
123
],
"excel_range": "<string>",
"sheet_name": "<string>",
"sheet_index": 123,
"workbook_sheet_index": 123,
"selected": true
}
],
"Footer": [
{
"id": "<string>",
"content": "<string>",
"page_number": 2,
"confidence": 0.5,
"reading_order": 1,
"bounding_box": [
123
],
"excel_range": "<string>",
"sheet_name": "<string>",
"sheet_index": 123,
"workbook_sheet_index": 123,
"selected": true
}
],
"markdown_with_ids": "<string>"
},
"extraction_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"extraction_url": "<string>",
"page_count": 2,
"failed_pages": [
{
"page": 2,
"error": "<string>"
}
],
"pages_succeeded": 1,
"pages_failed": 1,
"plan_info": {
"tier": "<string>",
"total_credits_used": 123,
"pages_used": 1,
"note": "<string>"
},
"warnings": [
"<string>"
],
"credits_used": 123,
"html": "<string>",
"chunks": {
"semantic": [
"<string>"
],
"header": [
"<string>"
],
"page": [
"<string>"
],
"recursive": [
"<string>"
]
},
"structured_output": {
"values": {},
"citations": {}
},
"input_schema": {},
"schema_error": "<string>",
"content": "<string>",
"job_id": "<string>",
"metadata": {}
}Jobs, Results & Webhooks
Download Large Result
Download the full result for an extraction when /extract or
GET /job/{jobId} returns is_url: true. The URL is single-use
for anonymous proxy access: after a successful download, subsequent
anonymous requests return 410 Gone. Same-org authenticated callers
may replay while the artifact is retained.
Legacy GET /large_results/{jobId} links remain supported as an alias.
GET
/
results
/
{jobId}
Download extraction result
curl --request GET \
--url https://api.runpulse.com/results/{jobId} \
--header 'x-api-key: <api-key>'import requests
url = "https://api.runpulse.com/results/{jobId}"
headers = {"x-api-key": "<api-key>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {'x-api-key': '<api-key>'}};
fetch('https://api.runpulse.com/results/{jobId}', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.runpulse.com/results/{jobId}",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
CURLOPT_HTTPHEADER => [
"x-api-key: <api-key>"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://api.runpulse.com/results/{jobId}"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("x-api-key", "<api-key>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://api.runpulse.com/results/{jobId}")
.header("x-api-key", "<api-key>")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.runpulse.com/results/{jobId}")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["x-api-key"] = '<api-key>'
response = http.request(request)
puts response.read_body{
"markdown": "<string>",
"extensions": {
"document_metadata": {
"file": {
"name": "<string>",
"extension": "<string>",
"media_type": "<string>",
"size_bytes": 1,
"sha256": "<string>"
},
"properties": {
"title": "<string>",
"authors": [
"<string>"
],
"subject": "<string>",
"description": "<string>",
"keywords": [
"<string>"
],
"language": "<string>",
"application": "<string>",
"application_version": "<string>",
"producer": "<string>",
"last_modified_by": "<string>",
"revision": "<string>",
"category": "<string>",
"content_status": "<string>",
"identifier": "<string>",
"version": "<string>",
"company": "<string>",
"manager": "<string>",
"template": "<string>",
"presentation_format": "<string>",
"editing_time_minutes": 1,
"copyright": "<string>",
"created_at": "<string>",
"modified_at": "<string>"
},
"structure": {
"page_count": 1,
"page_labels": [
"<string>"
],
"page_sizes": [
{}
],
"outline_count": 1,
"attachment_count": 1,
"annotation_count": 1,
"annotation_types": {},
"form_field_count": 1,
"sheet_count": 1,
"sheet_names": [
"<string>"
],
"sheet_visibility": {},
"active_sheet": "<string>",
"slide_count": 1,
"note_count": 1,
"hidden_slide_count": 1,
"multimedia_clip_count": 1,
"word_count": 1,
"character_count": 1,
"character_count_with_spaces": 1,
"line_count": 1,
"paragraph_count": 1,
"paragraph_count_derived": 1,
"table_count": 1,
"section_count": 1,
"embedded_image_count": 1,
"width_px": 1,
"height_px": 1,
"frame_count": 1,
"row_count": 1,
"max_column_count": 1
},
"warnings": [
"<string>"
],
"custom": {},
"format_specific": {}
},
"chunking": {
"semantic": [
"<string>"
],
"header": [
"<string>"
],
"page": [
"<string>"
],
"recursive": [
"<string>"
]
},
"footnoteReferences": [
{
"symbol": "<string>",
"footnoteTextId": "<string>",
"footnotePageNumber": 2,
"footnoteText": "<string>",
"referenceTextIds": [
"<string>"
],
"references": [
{
"textId": "<string>",
"tableId": "<string>",
"row": 123,
"column": 123,
"pageNumber": 2,
"markerBoundingBox": [
123
],
"source": "native"
}
]
}
],
"altOutputs": {
"wlbb": {
"words": [
{
"id": "<string>",
"text": "<string>",
"page_number": 2,
"bounding_box": [
123
],
"average_word_confidence": 123
}
],
"error": "<string>"
},
"html": "<string>",
"xml": "<string>"
}
},
"bounding_boxes": {
"Images": [
{
"id": "<string>",
"visual_type": "chart",
"content": "<string>",
"caption": "<string>",
"page_number": 2,
"confidence": 123,
"bounding_box": [
123
],
"image_url": "<string>",
"description": "<string>",
"classification": {
"confidence": 0.5,
"model": "<string>",
"error": "<string>"
},
"sheet_name": "<string>",
"sheet_index": 123,
"workbook_sheet_index": 123,
"excel_range": "<string>",
"chart_type": "<string>",
"chart_title": "<string>",
"source_ranges": [
"<string>"
],
"render_error": "<string>",
"description_error": "<string>"
}
],
"Tables": [
{
"table_info": {
"id": "<string>",
"dimensions": [
123
],
"excel_range": "<string>",
"sheet_name": "<string>",
"sheet_index": 123,
"workbook_sheet_index": 123,
"section_index": 123,
"section_type": "<string>",
"section_name": "<string>",
"table_name": "<string>",
"layout_type": "<string>",
"is_chart": true,
"chart_type": "<string>",
"chart_title": "<string>",
"source_ranges": [
"<string>"
],
"location": {},
"confidence": 0.5
},
"confidence": 0.5,
"cell_data": [
{
"confidence": 0.5
}
]
}
],
"Text": [
{
"id": "<string>",
"content": "<string>",
"page_number": 2,
"confidence": 0.5,
"reading_order": 1,
"bounding_box": [
123
],
"excel_range": "<string>",
"sheet_name": "<string>",
"sheet_index": 123,
"workbook_sheet_index": 123,
"selected": true
}
],
"Title": [
{
"id": "<string>",
"content": "<string>",
"page_number": 2,
"confidence": 0.5,
"reading_order": 1,
"bounding_box": [
123
],
"excel_range": "<string>",
"sheet_name": "<string>",
"sheet_index": 123,
"workbook_sheet_index": 123,
"selected": true
}
],
"Footer": [
{
"id": "<string>",
"content": "<string>",
"page_number": 2,
"confidence": 0.5,
"reading_order": 1,
"bounding_box": [
123
],
"excel_range": "<string>",
"sheet_name": "<string>",
"sheet_index": 123,
"workbook_sheet_index": 123,
"selected": true
}
],
"markdown_with_ids": "<string>"
},
"extraction_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"extraction_url": "<string>",
"page_count": 2,
"failed_pages": [
{
"page": 2,
"error": "<string>"
}
],
"pages_succeeded": 1,
"pages_failed": 1,
"plan_info": {
"tier": "<string>",
"total_credits_used": 123,
"pages_used": 1,
"note": "<string>"
},
"warnings": [
"<string>"
],
"credits_used": 123,
"html": "<string>",
"chunks": {
"semantic": [
"<string>"
],
"header": [
"<string>"
],
"page": [
"<string>"
],
"recursive": [
"<string>"
]
},
"structured_output": {
"values": {},
"citations": {}
},
"input_schema": {},
"schema_error": "<string>",
"content": "<string>",
"job_id": "<string>",
"metadata": {}
}Overview
Large results may be returned as a URL instead of an inline response body. Use this endpoint to download the full completed result for a job when an extract or job response includesis_url: true.
Large-result links are intended for completed jobs. Poll
GET /job/{jobId} first, then download the result URL if the job response says the result is URL-backed.Typical Flow
Related
Working With Large Documents
Plan long-running and large-output workflows.
Poll Job
Check async job status.
Authorizations
Headers
The API version. These pages document version 1.
Available options:
1 Path Parameters
Job identifier from the extraction response.
Response
Full extraction result (streamed JSON)
Full extraction result returned by the synchronous /extract endpoint. Inherits all core fields and adds deprecated backward-compatibility fields.
Primary markdown content extracted from the document. Always present in the new format.
Output from enabled extensions. Each key corresponds to an extension that was enabled in the request under extensions.*. Only keys for enabled extensions are present.
Show child attributes
Show child attributes
Positional bounding-box data for text, titles, headers, footers, images, and tables. Images carries chart/image visuals (with image_url when figure_processing.show_images is enabled), Tables the detected tables, and Text/Title/Footer the paragraph/title/footer regions. Additional keys (e.g. markdown_with_ids, defined_names) round-trip without being typed.
Show child attributes
Show child attributes
Persisted extraction ID. Present when storage is enabled (default). Use this ID with /split and /schema endpoints.
URL to view the extraction on the Pulse platform. Present when storage is enabled.
Number of pages processed.
Required range:
x >= 1Large documents only: the pages that could not be extracted, each {page, error}; [] when every page was extracted. The job still completes, and page_count stays the document's page count.
Show child attributes
Show child attributes
Large documents only: pages extracted (and billed).
Required range:
x >= 0Large documents only: pages that could not be extracted; 0 when none.
Required range:
x >= 0Billing tier and cumulative usage information. Includes total_credits_used (primary billing metric) and pages_used (legacy compatibility).
Show child attributes
Show child attributes
Non-fatal warnings generated during extraction. Includes deprecation notices when legacy input parameters are used, as well as processing warnings (e.g. word-level bounding box limitations).
Number of credits consumed by this request. Only present when the organization has the credit billing system enabled.
Deprecated — Use extensions.altOutputs.html instead. HTML representation of the extracted content. Present when the legacy returnHtml input was used.
Deprecated — Use extensions.chunking instead. Document content split into chunks. Present when the legacy chunking input was used.
Show child attributes
Show child attributes
Deprecated — Only present when the deprecated structuredOutput input parameter was used. Use the /schema endpoint after extraction instead.
Show child attributes
Show child attributes
Deprecated — Echo of the schema that was applied. Only present when the deprecated structuredOutput input parameter was used.
Deprecated — Error message if schema processing failed via the deprecated structuredOutput input parameter.
Deprecated — Alias for markdown. Included for backward compatibility with older SDK versions. Prefer markdown.
Deprecated — Identifier assigned to the extraction job. Retained for backward compatibility.
Deprecated — Additional metadata supplied by the backend. Retained for backward compatibility.