MinerU

MinerU integration (AI, Productivity). Imported from open-connector.

API key4 toolshttps://mineru.net

POST

mineru_create_extract_task

Create a MinerU precise extraction task from a document URL.

/api/v4/extract/task

11 parameters

Param	Type	Required	Description
url	string	required	The public HTTP or HTTPS URL of the document to parse with MinerU.
is_ocr	boolean	optional	Whether to enable OCR. Only applies to pipeline and vlm models.
enable_formula	boolean	optional	Whether to enable formula recognition for pipeline and vlm models.
enable_table	boolean	optional	Whether to enable table recognition for pipeline and vlm models.
language	string	optional	The document language code used by pipeline and vlm models.
data_id	string	optional	The caller-defined data identifier associated with the source document.
extra_formats	array	optional	Additional result formats to export besides Markdown and JSON.
page_ranges	string	optional	The page range expression to parse, such as 2,4-6 or 2--2.
model_version	string	optional	The MinerU model version to use for parsing.
no_cache	boolean	optional	Whether MinerU should bypass its URL content cache.
cache_tolerance	integer	optional	The acceptable MinerU URL cache age in seconds when no_cache is false.

GET

mineru_get_extract_task

Get the current status and result URLs for a MinerU extraction task.

/api/v4/extract/task/{task_id}

1 parameter

Param	Type	Required	Description
task_id	string	required	The MinerU extraction task identifier.

POST

mineru_create_extract_batch

Create a MinerU precise extraction batch from document URLs.

/api/v4/extract/task/batch

8 parameters

Param	Type	Required	Description
files	array	required	The URL-based documents to submit for batch parsing.
enable_formula	boolean	optional	Whether to enable formula recognition for pipeline and vlm models.
enable_table	boolean	optional	Whether to enable table recognition for pipeline and vlm models.
language	string	optional	The document language code used by pipeline and vlm models.
extra_formats	array	optional	Additional result formats to export besides Markdown and JSON.
model_version	string	optional	The MinerU model version to use for parsing.
no_cache	boolean	optional	Whether MinerU should bypass its URL content cache.
cache_tolerance	integer	optional	The acceptable MinerU URL cache age in seconds when no_cache is false.

GET

mineru_get_extract_batch_results

Get the current status and result URLs for a MinerU extraction batch.

/api/v4/extract-results/batch/{batch_id}

1 parameter

Param	Type	Required	Description
batch_id	string	required	The MinerU batch extraction task identifier.