Create Async Job
Submit multiple documents for asynchronous information extraction processing.
Authorization
AuthorizationRequiredBearer <token>
In: header
Request Body
multipart/form-dataRequiredmodelRequiredstring
Model name for information extraction
documentsRequiredarray<string>
User uploaded files. Multiple files can be uploaded with a limit of 20 files
schemaRequiredstring | string
Schema file or JSON string that must follow the schema format
modeBetastring
Extraction mode. "standard" is the default mode. "enhanced" mode provides better robustness for complex tables, poor quality scans, and handwritten text.
"standard"Value in: "standard" | "enhanced"locationBetaboolean
When set to true, returns the location of extracted values in the original document, including page number and bounding box coordinates. The bounding box is defined by 4 coordinates (x,y), where x and y values are normalized between 0 and 1.
falselocation_granularityBetastring
Specifies the granularity of the location coordinates. "element" returns the coordinates of the entire HTML element containing the extracted value. "word" returns the coordinates of the specific words matching the value.
"element"Value in: "element" | "word" | "all"splitBetaboolean
Automatically split and process multiple documents within a single file. When enabled, each document will be processed separately and return individual results.
falseconfidenceBetaboolean
When set to true, returns confidence levels ("high" or "low") for each extracted value. Our confidence scoring prioritizes high recall (>95%) to ensure potentially incorrect extractions are reliably flagged as "low" confidence, with approximately half of "low" confidence results being actually incorrect extractions (precision 50%).
falsechunkingBetaobject
Parameter for chunking documents into smaller parts for processing. Recommended for documents with 30+ pages or tables with 50+ rows to improve extraction performance.
Retrieve Job
Get detailed information about a specific information extraction job, including processing status and results.
Authorization
AuthorizationRequiredBearer <token>
In: header
Path Parameters
job_idRequiredstring
UUID of the information extraction job
Query Parameters
with_resultboolean
Whether to include extraction results in the response
List Jobs
Retrieve a paginated list of your information extraction jobs with filtering options.
Authorization
AuthorizationRequiredBearer <token>
In: header
Query Parameters
limitnumber
Maximum number of jobs to return per page
offsetnumber
Number of jobs to skip for pagination
statusstring
Filter jobs by status
Examples
Here's a typical workflow for using the async information extraction API:
Request
Response
Schema generation
Generate an extraction schema automatically from up to three sample documents. Covers the request body (model, messages), the chat.completion response carrying the schema, and an example request and response.
Document classification
Classify documents into user-defined types without templates or retraining β request parameters, examples, and response format.