API Reference

Beta

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Split

Create Split Job

POST/api/v1/beta/split/jobs

List Split Jobs

GET/api/v1/beta/split/jobs

Get Split Job

GET/api/v1/beta/split/jobs/{split_job_id}

ModelsExpand Collapse

SplitCategory = object { name, description }

Category definition for document splitting.

name: string

Name of the category.

maxLength200

minLength1

description: optional string

Optional description of what content belongs in this category.

maxLength2000

minLength1

SplitDocumentInput = object { type, value }

Document input specification for beta API.

type: string

Type of document input. Valid values are: file_id

value: string

Document identifier.

SplitResultResponse = object { segments }

Result of a completed split job.

segments: array of SplitSegmentResponse { category, confidence_category, pages }

List of document segments.

category: string

Category name this split belongs to.

confidence_category: string

Categorical confidence level. Valid values are: high, medium, low.

pages: array of number

1-indexed page numbers in this split.

SplitSegmentResponse = object { category, confidence_category, pages }

A segment of the split document.

category: string

Category name this split belongs to.

confidence_category: string

Categorical confidence level. Valid values are: high, medium, low.

pages: array of number

1-indexed page numbers in this split.

SplitCreateResponse = object { id, categories, document_input, 8 more }

Beta response — uses nested document_input object.

id: string

Unique identifier for the split job.

categories: array of SplitCategory { name, description }

Categories used for splitting.

name: string

Name of the category.

maxLength200

minLength1

description: optional string

Optional description of what content belongs in this category.

maxLength2000

minLength1

document_input: SplitDocumentInput { type, value }

Document that was split.

type: string

Type of document input. Valid values are: file_id

value: string

Document identifier.

project_id: string

Project ID this job belongs to.

status: string

Current status of the job. Valid values are: pending, processing, completed, failed, cancelled.

user_id: string

User ID who created this job.

configuration_id: optional string

Split configuration ID used for this job.

created_at: optional string

Creation datetime

formatdate-time

error_message: optional string

Error message if the job failed.

result: optional SplitResultResponse { segments }

Result of a completed split job.

segments: array of SplitSegmentResponse { category, confidence_category, pages }

List of document segments.

category: string

Category name this split belongs to.

confidence_category: string

Categorical confidence level. Valid values are: high, medium, low.

pages: array of number

1-indexed page numbers in this split.

updated_at: optional string

Update datetime

formatdate-time

SplitListResponse = object { id, categories, document_input, 8 more }

Beta response — uses nested document_input object.

id: string

Unique identifier for the split job.

categories: array of SplitCategory { name, description }

Categories used for splitting.

name: string

Name of the category.

maxLength200

minLength1

description: optional string

Optional description of what content belongs in this category.

maxLength2000

minLength1

document_input: SplitDocumentInput { type, value }

Document that was split.

type: string

Type of document input. Valid values are: file_id

value: string

Document identifier.

project_id: string

Project ID this job belongs to.

status: string

Current status of the job. Valid values are: pending, processing, completed, failed, cancelled.

user_id: string

User ID who created this job.

configuration_id: optional string

Split configuration ID used for this job.

created_at: optional string

Creation datetime

formatdate-time

error_message: optional string

Error message if the job failed.

result: optional SplitResultResponse { segments }

Result of a completed split job.

segments: array of SplitSegmentResponse { category, confidence_category, pages }

List of document segments.

category: string

Category name this split belongs to.

confidence_category: string

Categorical confidence level. Valid values are: high, medium, low.

pages: array of number

1-indexed page numbers in this split.

updated_at: optional string

Update datetime

formatdate-time

SplitGetResponse = object { id, categories, document_input, 8 more }

Beta response — uses nested document_input object.

id: string

Unique identifier for the split job.

categories: array of SplitCategory { name, description }

Categories used for splitting.

name: string

Name of the category.

maxLength200

minLength1

description: optional string

Optional description of what content belongs in this category.

maxLength2000

minLength1

document_input: SplitDocumentInput { type, value }

Document that was split.

type: string

Type of document input. Valid values are: file_id

value: string

Document identifier.

project_id: string

Project ID this job belongs to.

status: string

Current status of the job. Valid values are: pending, processing, completed, failed, cancelled.

user_id: string

User ID who created this job.

configuration_id: optional string

Split configuration ID used for this job.

created_at: optional string

Creation datetime

formatdate-time

error_message: optional string

Error message if the job failed.

result: optional SplitResultResponse { segments }

Result of a completed split job.

segments: array of SplitSegmentResponse { category, confidence_category, pages }

List of document segments.

category: string

Category name this split belongs to.

confidence_category: string

Categorical confidence level. Valid values are: high, medium, low.

pages: array of number

1-indexed page numbers in this split.

updated_at: optional string

Update datetime

formatdate-time