Extract

Create Extract Job

client.extract.create(, ?): ExtractV2Job { id, created_at, file_input, 9 more }

POST/api/v2/extract

List Extract Jobs

client.extract.list(?, ?): PaginatedCursor<ExtractV2Job { id, created_at, file_input, 9 more } >

GET/api/v2/extract

Get Extract Job

client.extract.get(, ?, ?): ExtractV2Job { id, created_at, file_input, 9 more }

GET/api/v2/extract/{job_id}

Delete Extract Job

client.extract.delete(, ?, ?): ExtractDeleteResponse

DELETE/api/v2/extract/{job_id}

Validate Extraction Schema

client.extract.validateSchema(, ?): ExtractV2SchemaValidateResponse { data_schema }

POST/api/v2/extract/schema/validation

Generate Extraction Schema

client.extract.generateSchema(, ?): ConfigurationCreate { name, parameters }

POST/api/v2/extract/schema/generate

ModelsExpand Collapse

ExtractConfiguration { data_schema, cite_sources, confidence_scores, 8 more }

Extract configuration combining parse and extract settings.

data_schema: Record<string, Record<string, unknown> | Array<unknown> | string | 2 more | null>

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

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

cite_sources?: boolean

Include citations in results

confidence_scores?: boolean

Include confidence scores in results

extract_version?: string

Extract algorithm version. Use ‘latest’ for the default pipeline, a date string (e.g. ‘2026-01-08’), or ‘continuous’ to opt into schema-guided splitting for documents with repeating entities.

extraction_target?: "per_doc" | "per_page" | "per_table_row"

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"

"per_page"

"per_table_row"

max_pages?: number | null

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

minimum1

parse_config_id?: string | null

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

parse_tier?: string | null

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

system_prompt?: string | null

Custom system prompt to guide extraction behavior

target_pages?: string | null

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

tier?: "cost_effective" | "agentic"

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

One of the following:

"cost_effective"

"agentic"

ExtractJobMetadata { field_metadata, parse_job_id, parse_tier }

Extraction metadata.

field_metadata?: ExtractedFieldMetadata { document_metadata, page_metadata, row_metadata } | null

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

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:

Record<string, unknown>

Array<unknown>

string

number

boolean

Per-page metadata when extraction_target is per_page

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

Per-row metadata when extraction_target is per_table_row

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

parse_job_id?: string | null

Reference to the ParseJob ID used for parsing

parse_tier?: string | null

Parse tier used for parsing the document

ExtractJobUsage { num_document_tokens, num_output_tokens, num_pages_extracted }

Extraction usage metrics.

num_document_tokens?: number | null

Number of document tokens

num_output_tokens?: number | null

Number of output tokens

num_pages_extracted?: number | null

Number of pages extracted

ExtractV2Job { id, created_at, file_input, 9 more }

An extraction job.

id: string

Unique job identifier (job_id)

created_at: string

Creation timestamp

formatdate-time

file_input: string

File ID or parse job ID that was extracted

project_id: string

Project this job belongs to

status: string

Current job status.

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

updated_at: string

Last update timestamp

formatdate-time

configuration?: ExtractConfiguration { data_schema, cite_sources, confidence_scores, 8 more } | null

Extract configuration combining parse and extract settings.

data_schema: Record<string, Record<string, unknown> | Array<unknown> | string | 2 more | null>

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

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

cite_sources?: boolean

Include citations in results

confidence_scores?: boolean

Include confidence scores in results

extract_version?: string

extraction_target?: "per_doc" | "per_page" | "per_table_row"

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"

"per_page"

"per_table_row"

max_pages?: number | null

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

minimum1

parse_config_id?: string | null

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

parse_tier?: string | null

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

system_prompt?: string | null

Custom system prompt to guide extraction behavior

target_pages?: string | null

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

tier?: "cost_effective" | "agentic"

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

One of the following:

"cost_effective"

"agentic"

configuration_id?: string | null

Saved extract configuration ID used for this job, if any

error_message?: string | null

Error details when status is FAILED

extract_metadata?: ExtractJobMetadata { field_metadata, parse_job_id, parse_tier } | null

Extraction metadata.

field_metadata?: ExtractedFieldMetadata { document_metadata, page_metadata, row_metadata } | null

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

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

Per-page metadata when extraction_target is per_page

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

Per-row metadata when extraction_target is per_table_row

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

parse_job_id?: string | null

Reference to the ParseJob ID used for parsing

parse_tier?: string | null

Parse tier used for parsing the document

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:

Record<string, Record<string, unknown> | Array<unknown> | string | 2 more | null>

Record<string, unknown>

Array<unknown>

string

number

boolean

Array<Record<string, Record<string, unknown> | Array<unknown> | string | 2 more | null>>

Record<string, unknown>

Array<unknown>

string

number

boolean

metadata?: Metadata | null

Job-level metadata.

usage?: ExtractJobUsage { num_document_tokens, num_output_tokens, num_pages_extracted } | null

Extraction usage metrics.

num_document_tokens?: number | null

Number of document tokens

num_output_tokens?: number | null

Number of output tokens

num_pages_extracted?: number | null

Number of pages extracted

ExtractV2JobCreate { file_input, configuration, configuration_id, webhook_configurations }

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

file_input: string

File ID or parse job ID to extract from

maxLength200

configuration?: ExtractConfiguration { data_schema, cite_sources, confidence_scores, 8 more } | null

Extract configuration combining parse and extract settings.

data_schema: Record<string, Record<string, unknown> | Array<unknown> | string | 2 more | null>

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

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

cite_sources?: boolean

Include citations in results

confidence_scores?: boolean

Include confidence scores in results

extract_version?: string

extraction_target?: "per_doc" | "per_page" | "per_table_row"

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"

"per_page"

"per_table_row"

max_pages?: number | null

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

minimum1

parse_config_id?: string | null

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

parse_tier?: string | null

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

system_prompt?: string | null

Custom system prompt to guide extraction behavior

target_pages?: string | null

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

tier?: "cost_effective" | "agentic"

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

One of the following:

"cost_effective"

"agentic"

configuration_id?: string | null

Saved configuration ID

webhook_configurations?: Array<WebhookConfiguration> | null

Outbound webhook endpoints to notify on job status changes

webhook_events?: Array<"extract.pending" | "extract.success" | "extract.error" | 14 more> | null

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

One of the following:

"extract.pending"

"extract.success"

"extract.error"

"extract.partial_success"

"extract.cancelled"

"parse.pending"

"parse.running"

"parse.success"

"parse.error"

"parse.partial_success"

"parse.cancelled"

"classify.pending"

"classify.success"

"classify.error"

"classify.partial_success"

"classify.cancelled"

"unmapped_event"

webhook_headers?: Record<string, string> | null

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

webhook_output_format?: string | null

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

webhook_url?: string | null

URL to receive webhook POST notifications

ExtractV2JobQueryResponse { items, next_page_token, total_size }

Paginated list of extraction jobs.

items: Array<ExtractV2Job { id, created_at, file_input, 9 more } >

The list of items.

id: string

Unique job identifier (job_id)

created_at: string

Creation timestamp

formatdate-time

file_input: string

File ID or parse job ID that was extracted

project_id: string

Project this job belongs to

status: string

Current job status.

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

updated_at: string

Last update timestamp

formatdate-time

configuration?: ExtractConfiguration { data_schema, cite_sources, confidence_scores, 8 more } | null

Extract configuration combining parse and extract settings.

data_schema: Record<string, Record<string, unknown> | Array<unknown> | string | 2 more | null>

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

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

cite_sources?: boolean

Include citations in results

confidence_scores?: boolean

Include confidence scores in results

extract_version?: string

extraction_target?: "per_doc" | "per_page" | "per_table_row"

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"

"per_page"

"per_table_row"

max_pages?: number | null

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

minimum1

parse_config_id?: string | null

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

parse_tier?: string | null

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

system_prompt?: string | null

Custom system prompt to guide extraction behavior

target_pages?: string | null

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

tier?: "cost_effective" | "agentic"

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

One of the following:

"cost_effective"

"agentic"

configuration_id?: string | null

Saved extract configuration ID used for this job, if any

error_message?: string | null

Error details when status is FAILED

extract_metadata?: ExtractJobMetadata { field_metadata, parse_job_id, parse_tier } | null

Extraction metadata.

field_metadata?: ExtractedFieldMetadata { document_metadata, page_metadata, row_metadata } | null

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

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

Per-page metadata when extraction_target is per_page

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

Per-row metadata when extraction_target is per_table_row

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

parse_job_id?: string | null

Reference to the ParseJob ID used for parsing

parse_tier?: string | null

Parse tier used for parsing the document

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:

Record<string, Record<string, unknown> | Array<unknown> | string | 2 more | null>

Record<string, unknown>

Array<unknown>

string

number

boolean

Array<Record<string, Record<string, unknown> | Array<unknown> | string | 2 more | null>>

Record<string, unknown>

Array<unknown>

string

number

boolean

metadata?: Metadata | null

Job-level metadata.

usage?: ExtractJobUsage { num_document_tokens, num_output_tokens, num_pages_extracted } | null

Extraction usage metrics.

num_document_tokens?: number | null

Number of document tokens

num_output_tokens?: number | null

Number of output tokens

num_pages_extracted?: number | null

Number of pages extracted

next_page_token?: string | null

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

total_size?: number | null

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.

ExtractV2SchemaGenerateRequest { data_schema, file_id, name, prompt }

Request schema for generating an extraction schema.

Optional schema to validate, refine, or extend

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

file_id?: string | null

Optional file ID to analyze for schema generation

name?: string | null

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

maxLength255

prompt?: string | null

Natural language description of the data structure to extract

ExtractV2SchemaValidateRequest { data_schema }

Request schema for validating an extraction schema.

data_schema: Record<string, Record<string, unknown> | Array<unknown> | string | 2 more | null>

JSON Schema to validate for use with extract jobs

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

ExtractV2SchemaValidateResponse { data_schema }

Response schema for schema validation.

data_schema: Record<string, Record<string, unknown> | Array<unknown> | string | 2 more | null>

Validated JSON Schema, ready for use in extract jobs

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

ExtractedFieldMetadata { document_metadata, page_metadata, row_metadata }

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

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

Per-page metadata when extraction_target is per_page

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

Per-row metadata when extraction_target is per_table_row

One of the following:

Record<string, unknown>

Array<unknown>

string

number

boolean

ExtractDeleteResponse = unknown