OCR [BETA]
This endpoint is currently in beta. For any issues or feedback, please contact us via Discord or support@cortecs.ai.
This endpoint extracts text and structured content from a document or image using the specified OCR model.
Authorizations
AuthorizationstringRequired
Bearer authentication header of the form Bearer <token>.
Body
A request object for processing a document or image and controlling router behavior.
preferencestring · enumOptionalPossible values:
The provider preference for handling the request.
allowed_providersstring[] · nullableOptional
The providers that are allowed to process the request.
eu_nativeboolean · nullableOptional
Whether to use only providers based and regulated within the EU.
allow_quantizationboolean · nullableOptional
Whether to allow quantized endpoints.
allow_zero_data_retentionboolean · nullableOptional
Whether to use only zero-data-retention providers.
enable_model_fallbackboolean · nullableOptional
Whether to allow model fallback when the requested model is unavailable.
fallbacksstring[] · nullableOptional
Fallback model names to try when the requested model is unavailable.
modelstringRequired
documentone ofRequired
or
pagesone ofOptional
integer[]Optional
stringOptional
include_image_base64booleanOptional
image_limitinteger · nullableOptional
image_min_sizeinteger · nullableOptional
include_blocksbooleanOptionalDefault:
truedocument_annotation_formatobjectOptional
bbox_annotation_formatobjectOptional
document_annotation_promptstringOptional
extract_headerbooleanOptional
extract_footerbooleanOptional
table_formatstring · enumOptionalPossible values:
confidence_scores_granularitystring · enumOptionalPossible values:
Responses
200
OCR result
application/json
objectstring · enumRequiredPossible values:
modelstringRequired
document_annotationone of · nullableOptional
objectOptional
stringOptional
500
Internal server error.
post/ocr
curl https://api.cortecs.ai/v1/ocr \
-H "Authorization: Bearer $CORTECS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"mistral-ocr-4.1","document":{"type":"document_url","document_url":"https://example.com/document.pdf"}}'
{
"object": "ocr",
"model": "text",
"pages": [
{
"index": 1,
"markdown": "text",
"images": [
{}
]
}
],
"document_annotation": {},
"usage_info": {
"pages_processed": 1,
"credits": 1
}
}Last updated