API Reference

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Extract

Create Extract Job

ExtractV2Job Extract.Create(ExtractCreateParamsparameters, CancellationTokencancellationToken = default)

POST/api/v2/extract

List Extract Jobs

ExtractV2JobQueryResponse Extract.List(ExtractListParams?parameters, CancellationTokencancellationToken = default)

GET/api/v2/extract

Get Extract Job

ExtractV2Job Extract.Get(ExtractGetParamsparameters, CancellationTokencancellationToken = default)

GET/api/v2/extract/{job_id}

Delete Extract Job

JsonElement Extract.Delete(ExtractDeleteParamsparameters, CancellationTokencancellationToken = default)

DELETE/api/v2/extract/{job_id}

Validate Extraction Schema

ExtractV2SchemaValidateResponse Extract.ValidateSchema(ExtractValidateSchemaParamsparameters, CancellationTokencancellationToken = default)

POST/api/v2/extract/schema/validation

Generate Extraction Schema

ConfigurationCreate Extract.GenerateSchema(ExtractGenerateSchemaParams?parameters, CancellationTokencancellationToken = default)

POST/api/v2/extract/schema/generate

ModelsExpand Collapse

class ExtractConfiguration:

Extract configuration combining parse and extract settings.

required IReadOnlyDictionary<string, DataSchema?> DataSchema

JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first.

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

Boolean CiteSources

Include citations in results

Boolean ConfidenceScores

Include confidence scores in results

ExtractionTarget ExtractionTarget

Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row

One of the following:

"per_doc"PerDoc

"per_page"PerPage

"per_table_row"PerTableRow

Long? MaxPages

Maximum number of pages to process. Omit for no limit.

minimum1

string? ParseConfigID

Saved parse configuration ID to control how the document is parsed before extraction

string? ParseTier

Parse tier to use before extraction. Defaults to the extract tier if not specified.

string? SystemPrompt

Custom system prompt to guide extraction behavior

string? TargetPages

Comma-separated page numbers or ranges to process (1-based). Omit to process all pages.

Tier Tier

Extract tier: cost_effective (5 credits/page), agentic (15 credits/page), or agentic_plus (50 credits/page)

One of the following:

"agentic"Agentic

"agentic_plus"AgenticPlus

"cost_effective"CostEffective

string Version

Use ‘latest’ for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. Job responses always report the concrete resolved version the job runs, fixed at job creation; saved configurations keep the value as provided.

class ExtractJobMetadata:

Extraction metadata.

ExtractedFieldMetadata? FieldMetadata

Metadata for extracted fields including document, page, and row level info.

IReadOnlyDictionary<string, DocumentMetadata?>? DocumentMetadata

Per-field metadata keyed by field name from your schema. Scalar fields (e.g. vendor) map to a FieldMetadataEntry with citation and confidence. Array fields (e.g. items) map to a list where each element contains per-sub-field FieldMetadataEntry objects, indexed by array position. Nested objects contain sub-field entries recursively.

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

IReadOnlyList<IReadOnlyDictionary<string, PageMetadata?>>? PageMetadata

Per-page metadata when extraction_target is per_page

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

IReadOnlyList<IReadOnlyDictionary<string, RowMetadata?>>? RowMetadata

Per-row metadata when extraction_target is per_table_row

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

string? ParseJobID

Reference to the ParseJob ID used for parsing

string? ParseTier

Parse tier used for parsing the document

class ExtractJobUsage:

Extraction usage metrics.

Long? NumPagesBilled

Number of effective pages billed

Long? NumPagesExtracted

Number of pages extracted

class ExtractV2Job:

An extraction job.

required string ID

Unique job identifier (job_id)

required DateTimeOffset CreatedAt

Creation timestamp

formatdate-time

required string FileInput

File ID or parse job ID that was extracted

required string ProjectID

Project this job belongs to

required string Status

Current job status.

• PENDING — queued, not yet started
• RUNNING — actively processing
• COMPLETED — finished successfully
• FAILED — terminated with an error
• CANCELLED — cancelled by user

required DateTimeOffset UpdatedAt

Last update timestamp

formatdate-time

ExtractConfiguration? Configuration

Extract configuration combining parse and extract settings.

required IReadOnlyDictionary<string, DataSchema?> DataSchema

JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first.

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

Boolean CiteSources

Include citations in results

Boolean ConfidenceScores

Include confidence scores in results

ExtractionTarget ExtractionTarget

Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row

One of the following:

"per_doc"PerDoc

"per_page"PerPage

"per_table_row"PerTableRow

Long? MaxPages

Maximum number of pages to process. Omit for no limit.

minimum1

string? ParseConfigID

Saved parse configuration ID to control how the document is parsed before extraction

string? ParseTier

Parse tier to use before extraction. Defaults to the extract tier if not specified.

string? SystemPrompt

Custom system prompt to guide extraction behavior

string? TargetPages

Comma-separated page numbers or ranges to process (1-based). Omit to process all pages.

Tier Tier

Extract tier: cost_effective (5 credits/page), agentic (15 credits/page), or agentic_plus (50 credits/page)

One of the following:

"agentic"Agentic

"agentic_plus"AgenticPlus

"cost_effective"CostEffective

string Version

Use ‘latest’ for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. Job responses always report the concrete resolved version the job runs, fixed at job creation; saved configurations keep the value as provided.

string? ConfigurationID

Saved extract configuration ID used for this job, if any

string? ErrorMessage

Error details when status is FAILED

ExtractJobMetadata? ExtractMetadata

Extraction metadata.

ExtractedFieldMetadata? FieldMetadata

Metadata for extracted fields including document, page, and row level info.

IReadOnlyDictionary<string, DocumentMetadata?>? DocumentMetadata

Per-field metadata keyed by field name from your schema. Scalar fields (e.g. vendor) map to a FieldMetadataEntry with citation and confidence. Array fields (e.g. items) map to a list where each element contains per-sub-field FieldMetadataEntry objects, indexed by array position. Nested objects contain sub-field entries recursively.

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

IReadOnlyList<IReadOnlyDictionary<string, PageMetadata?>>? PageMetadata

Per-page metadata when extraction_target is per_page

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

IReadOnlyList<IReadOnlyDictionary<string, RowMetadata?>>? RowMetadata

Per-row metadata when extraction_target is per_table_row

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

string? ParseJobID

Reference to the ParseJob ID used for parsing

string? ParseTier

Parse tier used for parsing the document

ExtractResult? ExtractResult

Extracted data conforming to the data_schema. Returns a single object for per_doc, or an array for per_page / per_table_row.

One of the following:

IReadOnlyDictionary<string, UnionMember0Item?>

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

IReadOnlyList<IReadOnlyDictionary<string, UnnamedSchemaWithArrayParent1Item?>>

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

Metadata? Metadata

Job-level metadata.

ExtractJobUsage? Usage

Extraction usage metrics.

Long? NumPagesBilled

Number of effective pages billed

Long? NumPagesExtracted

Number of pages extracted

class ExtractV2JobCreate:

Request to create an extraction job. Provide configuration_id or inline configuration.

required string FileInput

File ID or parse job ID to extract from

maxLength200

ExtractConfiguration? Configuration

Extract configuration combining parse and extract settings.

required IReadOnlyDictionary<string, DataSchema?> DataSchema

JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first.

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

Boolean CiteSources

Include citations in results

Boolean ConfidenceScores

Include confidence scores in results

ExtractionTarget ExtractionTarget

Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row

One of the following:

"per_doc"PerDoc

"per_page"PerPage

"per_table_row"PerTableRow

Long? MaxPages

Maximum number of pages to process. Omit for no limit.

minimum1

string? ParseConfigID

Saved parse configuration ID to control how the document is parsed before extraction

string? ParseTier

Parse tier to use before extraction. Defaults to the extract tier if not specified.

string? SystemPrompt

Custom system prompt to guide extraction behavior

string? TargetPages

Comma-separated page numbers or ranges to process (1-based). Omit to process all pages.

Tier Tier

Extract tier: cost_effective (5 credits/page), agentic (15 credits/page), or agentic_plus (50 credits/page)

One of the following:

"agentic"Agentic

"agentic_plus"AgenticPlus

"cost_effective"CostEffective

string Version

Use ‘latest’ for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. Job responses always report the concrete resolved version the job runs, fixed at job creation; saved configurations keep the value as provided.

string? ConfigurationID

Saved configuration ID

IReadOnlyList<WebhookConfiguration>? WebhookConfigurations

Outbound webhook endpoints to notify on job status changes

IReadOnlyList<WebhookEvent>? WebhookEvents

Events to subscribe to (e.g. ‘parse.success’, ‘extract.error’). If null, all events are delivered.

One of the following:

"classify.cancelled"ClassifyCancelled

"classify.error"ClassifyError

"classify.partial_success"ClassifyPartialSuccess

"classify.pending"ClassifyPending

"classify.running"ClassifyRunning

"classify.success"ClassifySuccess

"extract.cancelled"ExtractCancelled

"extract.error"ExtractError

"extract.partial_success"ExtractPartialSuccess

"extract.pending"ExtractPending

"extract.success"ExtractSuccess

"parse.cancelled"ParseCancelled

"parse.error"ParseError

"parse.partial_success"ParsePartialSuccess

"parse.pending"ParsePending

"parse.running"ParseRunning

"parse.success"ParseSuccess

"sheets.cancelled"SheetsCancelled

"sheets.error"SheetsError

"sheets.partial_success"SheetsPartialSuccess

"sheets.pending"SheetsPending

"sheets.success"SheetsSuccess

"split.cancelled"SplitCancelled

"split.error"SplitError

"split.pending"SplitPending

"split.processing"SplitProcessing

"split.success"SplitSuccess

"unmapped_event"UnmappedEvent

IReadOnlyDictionary<string, string>? WebhookHeaders

Custom HTTP headers sent with each webhook request (e.g. auth tokens)

string? WebhookOutputFormat

Response format sent to the webhook: ‘string’ (default) or ‘json’

string? WebhookSigningSecret

Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the ‘LC-Signature’ header (value ‘sha256=’). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic.

string? WebhookUrl

URL to receive webhook POST notifications

class ExtractV2JobQueryResponse:

Paginated list of extraction jobs.

required IReadOnlyList<ExtractV2Job> Items

The list of items.

required string ID

Unique job identifier (job_id)

required DateTimeOffset CreatedAt

Creation timestamp

formatdate-time

required string FileInput

File ID or parse job ID that was extracted

required string ProjectID

Project this job belongs to

required string Status

Current job status.

• PENDING — queued, not yet started
• RUNNING — actively processing
• COMPLETED — finished successfully
• FAILED — terminated with an error
• CANCELLED — cancelled by user

required DateTimeOffset UpdatedAt

Last update timestamp

formatdate-time

ExtractConfiguration? Configuration

Extract configuration combining parse and extract settings.

required IReadOnlyDictionary<string, DataSchema?> DataSchema

JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first.

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

Boolean CiteSources

Include citations in results

Boolean ConfidenceScores

Include confidence scores in results

ExtractionTarget ExtractionTarget

Granularity of extraction: per_doc returns one object per document, per_page returns one object per page, per_table_row returns one object per table row

One of the following:

"per_doc"PerDoc

"per_page"PerPage

"per_table_row"PerTableRow

Long? MaxPages

Maximum number of pages to process. Omit for no limit.

minimum1

string? ParseConfigID

Saved parse configuration ID to control how the document is parsed before extraction

string? ParseTier

Parse tier to use before extraction. Defaults to the extract tier if not specified.

string? SystemPrompt

Custom system prompt to guide extraction behavior

string? TargetPages

Comma-separated page numbers or ranges to process (1-based). Omit to process all pages.

Tier Tier

Extract tier: cost_effective (5 credits/page), agentic (15 credits/page), or agentic_plus (50 credits/page)

One of the following:

"agentic"Agentic

"agentic_plus"AgenticPlus

"cost_effective"CostEffective

string Version

Use ‘latest’ for the latest release for the selected tier or a date string (YYYY-MM-DD format) to pin to the nearest release at or before that date. Job responses always report the concrete resolved version the job runs, fixed at job creation; saved configurations keep the value as provided.

string? ConfigurationID

Saved extract configuration ID used for this job, if any

string? ErrorMessage

Error details when status is FAILED

ExtractJobMetadata? ExtractMetadata

Extraction metadata.

ExtractedFieldMetadata? FieldMetadata

Metadata for extracted fields including document, page, and row level info.

IReadOnlyDictionary<string, DocumentMetadata?>? DocumentMetadata

Per-field metadata keyed by field name from your schema. Scalar fields (e.g. vendor) map to a FieldMetadataEntry with citation and confidence. Array fields (e.g. items) map to a list where each element contains per-sub-field FieldMetadataEntry objects, indexed by array position. Nested objects contain sub-field entries recursively.

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

IReadOnlyList<IReadOnlyDictionary<string, PageMetadata?>>? PageMetadata

Per-page metadata when extraction_target is per_page

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

IReadOnlyList<IReadOnlyDictionary<string, RowMetadata?>>? RowMetadata

Per-row metadata when extraction_target is per_table_row

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

string? ParseJobID

Reference to the ParseJob ID used for parsing

string? ParseTier

Parse tier used for parsing the document

ExtractResult? ExtractResult

Extracted data conforming to the data_schema. Returns a single object for per_doc, or an array for per_page / per_table_row.

One of the following:

IReadOnlyDictionary<string, UnionMember0Item?>

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

IReadOnlyList<IReadOnlyDictionary<string, UnnamedSchemaWithArrayParent1Item?>>

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

Metadata? Metadata

Job-level metadata.

ExtractJobUsage? Usage

Extraction usage metrics.

Long? NumPagesBilled

Number of effective pages billed

Long? NumPagesExtracted

Number of pages extracted

string? NextPageToken

A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages.

Long? TotalSize

The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only.

class ExtractV2SchemaGenerateRequest:

Request schema for generating an extraction schema.

IReadOnlyDictionary<string, DataSchema?>? DataSchema

Optional schema to validate, refine, or extend

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

string? FileID

Optional file ID to analyze for schema generation

string? Name

Name for the generated configuration (auto-generated if omitted)

maxLength255

string? Prompt

Natural language description of the data structure to extract

class ExtractV2SchemaValidateRequest:

Request schema for validating an extraction schema.

required IReadOnlyDictionary<string, DataSchema?> DataSchema

JSON Schema to validate for use with extract jobs

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

class ExtractV2SchemaValidateResponse:

Response schema for schema validation.

required IReadOnlyDictionary<string, DataSchema?> DataSchema

Validated JSON Schema, ready for use in extract jobs

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

class ExtractedFieldMetadata:

Metadata for extracted fields including document, page, and row level info.

IReadOnlyDictionary<string, DocumentMetadata?>? DocumentMetadata

Per-field metadata keyed by field name from your schema. Scalar fields (e.g. vendor) map to a FieldMetadataEntry with citation and confidence. Array fields (e.g. items) map to a list where each element contains per-sub-field FieldMetadataEntry objects, indexed by array position. Nested objects contain sub-field entries recursively.

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

IReadOnlyList<IReadOnlyDictionary<string, PageMetadata?>>? PageMetadata

Per-page metadata when extraction_target is per_page

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean

IReadOnlyList<IReadOnlyDictionary<string, RowMetadata?>>? RowMetadata

Per-row metadata when extraction_target is per_table_row

One of the following:

IReadOnlyDictionary<string, JsonElement>

IReadOnlyList<JsonElement>

string

Double

Boolean