Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Orq MCP is live: Use natural language to interrogate traces, spot regressions, and experiment your way to optimal AI configurations. Available in Claude Desktop, Claude Code, Cursor, and more. Start now →
Extracts text content while maintaining document structure and hierarchy
curl --request POST \
--url https://api.orq.ai/v2/router/ocr \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "<string>",
"document": {
"type": "document_url",
"document_url": "<string>",
"document_name": "<string>"
},
"pages": [
123
],
"ocr_settings": {
"include_image_base64": true,
"max_images_to_include": 123,
"image_min_size": 123
}
}
'const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model: '<string>',
document: {type: 'document_url', document_url: '<string>', document_name: '<string>'},
pages: [123],
ocr_settings: {include_image_base64: true, max_images_to_include: 123, image_min_size: 123}
})
};
fetch('https://api.orq.ai/v2/router/ocr', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));import requests
url = "https://api.orq.ai/v2/router/ocr"
payload = {
"model": "<string>",
"document": {
"type": "document_url",
"document_url": "<string>",
"document_name": "<string>"
},
"pages": [123],
"ocr_settings": {
"include_image_base64": True,
"max_images_to_include": 123,
"image_min_size": 123
}
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text){
"model": "<string>",
"pages": [
{
"index": 123,
"markdown": "<string>",
"images": [
{
"id": "<string>",
"image_base64": "<string>"
}
],
"dimensions": {
"dpi": 123,
"height": 123,
"width": 123
}
}
],
"usage": {
"type": "pages",
"pages_processed": 123
}
}Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
input
ID of the model to use for OCR.
Document to run OCR on. Can be a DocumentURLChunk or ImageURLChunk.
Show child attributes
Specific pages to process. Can be a single number, range, or list. Starts from 0. Null for all pages.
Optional settings for the OCR run
Show child attributes
Was this page helpful?
curl --request POST \
--url https://api.orq.ai/v2/router/ocr \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "<string>",
"document": {
"type": "document_url",
"document_url": "<string>",
"document_name": "<string>"
},
"pages": [
123
],
"ocr_settings": {
"include_image_base64": true,
"max_images_to_include": 123,
"image_min_size": 123
}
}
'const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
model: '<string>',
document: {type: 'document_url', document_url: '<string>', document_name: '<string>'},
pages: [123],
ocr_settings: {include_image_base64: true, max_images_to_include: 123, image_min_size: 123}
})
};
fetch('https://api.orq.ai/v2/router/ocr', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));import requests
url = "https://api.orq.ai/v2/router/ocr"
payload = {
"model": "<string>",
"document": {
"type": "document_url",
"document_url": "<string>",
"document_name": "<string>"
},
"pages": [123],
"ocr_settings": {
"include_image_base64": True,
"max_images_to_include": 123,
"image_min_size": 123
}
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text){
"model": "<string>",
"pages": [
{
"index": 123,
"markdown": "<string>",
"images": [
{
"id": "<string>",
"image_base64": "<string>"
}
],
"dimensions": {
"dpi": 123,
"height": 123,
"width": 123
}
}
],
"usage": {
"type": "pages",
"pages_processed": 123
}
}