> ## Documentation Index
> Fetch the complete documentation index at: https://docs.extend.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Get Splitter
GET https://api.extend.ai/splitters/{id}
Get details of a splitter.
Reference: https://docs.extend.ai/api-reference/endpoints/split/get-splitter
## OpenAPI Specification
```yaml
openapi: 3.1.0
info:
title: 2026_02_09_docs
version: 1.0.0
paths:
/splitters/{id}:
get:
operationId: retrieve
summary: Get Splitter
description: Get details of a splitter.
tags:
- subpackage_splitters
parameters:
- name: id
in: path
description: |
The ID of the splitter to get.
Example: `"spl_Xj8mK2pL9nR4vT7qY5wZ"`
required: true
schema:
type: string
- name: Authorization
in: header
description: Bearer authentication
required: true
schema:
type: string
- name: x-extend-api-version
in: header
description: >-
API version to use for the request. If you're using an SDK, you can
ignore this parameter. If you are not using an SDK and do not
specify a version, you will either receive a `400 Bad Request` or be
set to a previous legacy version. See [API
Versioning](https://docs.extend.ai/2026-02-09/api-reference/api-versioning)
for more details.
required: false
schema:
type: string
enum:
- '2026-02-09'
default: '2026-02-09'
- name: x-extend-workspace-id
in: header
description: >
The workspace ID to target. **Required** when using an
organization-scoped API key; optional for workspace-scoped keys (the
key is already tied to a workspace). See
[Authentication](https://docs.extend.ai/2026-02-09/api-reference/authentication)
for details on API key scopes.
required: false
schema:
type: string
responses:
'200':
description: Splitter details
content:
application/json:
schema:
$ref: '#/components/schemas/Splitter'
'400':
description: >
Standard error response format for all Extend API errors.
See the [Error Codes
documentation](https://docs.extend.ai/2026-02-09/api-reference/error-handling)
for error handling recommendations.
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'401':
description: >
Standard error response format for all Extend API errors.
See the [Error Codes
documentation](https://docs.extend.ai/2026-02-09/api-reference/error-handling)
for error handling recommendations.
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'402':
description: >
Standard error response format for all Extend API errors.
See the [Error Codes
documentation](https://docs.extend.ai/2026-02-09/api-reference/error-handling)
for error handling recommendations.
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'403':
description: >
Standard error response format for all Extend API errors.
See the [Error Codes
documentation](https://docs.extend.ai/2026-02-09/api-reference/error-handling)
for error handling recommendations.
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'404':
description: >
Standard error response format for all Extend API errors.
See the [Error Codes
documentation](https://docs.extend.ai/2026-02-09/api-reference/error-handling)
for error handling recommendations.
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'422':
description: >
Standard error response format for all Extend API errors.
See the [Error Codes
documentation](https://docs.extend.ai/2026-02-09/api-reference/error-handling)
for error handling recommendations.
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'429':
description: >
Standard error response format for all Extend API errors.
See the [Error Codes
documentation](https://docs.extend.ai/2026-02-09/api-reference/error-handling)
for error handling recommendations.
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
'500':
description: >
Standard error response format for all Extend API errors.
See the [Error Codes
documentation](https://docs.extend.ai/2026-02-09/api-reference/error-handling)
for error handling recommendations.
content:
application/json:
schema:
$ref: '#/components/schemas/ApiError'
servers:
- url: https://api.extend.ai
description: Production
- url: https://api.us2.extend.app
description: Production US2
- url: https://api.eu1.extend.ai
description: Production EU1
components:
schemas:
SplitterObject:
type: string
enum:
- splitter
description: The type of object. Will always be `"splitter"`.
title: SplitterObject
CreatedAt:
type: string
format: date-time
description: >
The time (in UTC) at which the object was created. Will follow the RFC
3339 format.
Example: `"2024-03-21T16:45:00Z"`
title: CreatedAt
UpdatedAt:
type: string
format: date-time
description: >
The time (in UTC) at which the object was last updated. Will follow the
RFC 3339 format.
Example: `"2024-03-21T16:45:00Z"`
title: UpdatedAt
SplitterVersionObject:
type: string
enum:
- splitter_version
description: The type of object. Will always be `"splitter_version"`.
title: SplitterVersionObject
SplitBaseProcessor:
type: string
enum:
- splitting_performance
- splitting_light
default: splitting_performance
description: >
The base processor to use. For splitters, this can be either
`"splitting_performance"` or `"splitting_light"`. Defaults to
`"splitting_performance"` if not provided. See [Splitting
Changelog](https://docs.extend.ai/2026-02-09/model-versioning/splitting/splitting-performance)
for more details.
title: SplitBaseProcessor
SplitClassification:
type: object
properties:
id:
type: string
description: >-
Unique identifier for the classification. We recommend lowercase,
underscore-separated format.
type:
type: string
description: Type identifier for the classification.
description:
type: string
description: A detailed description of the classification.
identifierKey:
type: string
description: >
A natural-language rule describing how to extract a unique
identifier for subdocuments of this type. For example, `"Extract the
invoice number from the document header"`.
When provided, the splitter will extract the specified identifier
for each subdocument of this type and include it in the output as
the `identifier` field. This enables merging of related subdocuments
that share the same extracted identifier.
**Availability:** Supported on `splitting_light` >= 1.3.0 and
`splitting_performance` >= 1.5.0. If provided on older versions,
this field is accepted but ignored.
required:
- id
- type
- description
description: >-
A classification for document splitting. Extends the base Classification
with an optional `identifierKey` field for per-type identifier
extraction rules.
title: SplitClassification
SplitClassifications:
type: array
items:
$ref: '#/components/schemas/SplitClassification'
description: >-
Array of split classifications that define the possible types of
document sections. Must provide at least one classification. At least
one classification must have the type `"other"`. Each classification
item must have a unique id.
title: SplitClassifications
SplitAdvancedOptionsSplitMethod:
type: string
enum:
- high_precision
- basic_precision
default: high_precision
description: >
The method to use for splitting documents. `high_precision` is more
accurate but slower, while `basic_precision` is faster but less precise.
**Deprecated:** For `splitting_light` >= 1.3.0 and
`splitting_performance` >= 1.5.0, this field has no impact and is
ignored if provided. It is still accepted for compatibility with older
integrations.
title: SplitAdvancedOptionsSplitMethod
PageRangesItems:
type: object
properties:
start:
type: integer
description: The start page of the range.
end:
type: integer
default: 750
description: The end page of the range.
required:
- start
- end
title: PageRangesItems
PageRanges:
type: array
items:
$ref: '#/components/schemas/PageRangesItems'
description: >-
Limit processing to the specified page ranges. See [Page
Ranges](https://docs.extend.ai/2026-02-09/page-ranges).
title: PageRanges
SplitAdvancedOptions:
type: object
properties:
splitIdentifierRules:
type: string
description: >
Custom rules for identifying split points.
**Deprecated:** For `splitting_light` >= 1.3.0 and
`splitting_performance` >= 1.5.0, use the `identifierKey` field on
each classification in `splitClassifications` instead. This provides
per-type identifier extraction rules rather than a single global
rule. On those versions, this field is accepted but ignored if
provided.
splitMethod:
$ref: '#/components/schemas/SplitAdvancedOptionsSplitMethod'
default: high_precision
description: >
The method to use for splitting documents. `high_precision` is more
accurate but slower, while `basic_precision` is faster but less
precise.
**Deprecated:** For `splitting_light` >= 1.3.0 and
`splitting_performance` >= 1.5.0, this field has no impact and is
ignored if provided. It is still accepted for compatibility with
older integrations.
splitExcelDocumentsBySheetEnabled:
type: boolean
default: false
description: For Excel documents, split by worksheet.
pageRanges:
$ref: '#/components/schemas/PageRanges'
pageOverlapEnabled:
type: boolean
default: false
description: >
When enabled, the splitter will allow for page overlap when
splitting a document such that a page can occur in multiple adjacent
splits when context from the previous split is on the page and
context from the next split is on the page.
**Availability:** Supported on `splitting_light` >= 1.1.0 and
`splitting_performance` >= 1.2.0. If provided on older versions,
this field is accepted but ignored.
title: SplitAdvancedOptions
ParseConfigTarget:
type: string
enum:
- markdown
- spatial
default: markdown
description: >
The target format for the parsed content.
Supported values:
* `markdown`: True markdown with logical reading order (headings, lists,
tables, checkboxes). Best default for LLMs/RAG and enables section-based
chunking.
* `spatial`: Layout/position-preserving text that uses markdown elements
for block types but is not strictly markdown due to whitespace/tabs used
to maintain placement. Only page-based chunking is supported.
Guidance:
* Prefer `markdown` for most documents, multi-column reading order, and
retrieval use cases
* Prefer `spatial` for messy/scanned/handwritten or skewed documents,
when you need near 1:1 layout fidelity, or for BOL-like logistics docs
See “Markdown vs Spatial” in the [Parse
guide](https://docs.extend.ai/2026-02-09/parsing/configuration#target-format)
for details.
title: ParseConfigTarget
ParseConfigChunkingStrategyType:
type: string
enum:
- page
- document
- section
default: page
description: >
The type of chunking strategy. Supported values:
* `page`: Chunk document by pages.
* `document`: Entire document is a single chunk. Essentially no
chunking.
* `section`: Split by logical sections. Not supported for
target=spatial.
title: ParseConfigChunkingStrategyType
ParseConfigChunkingStrategyOptions:
type: object
properties:
minCharacters:
type: integer
default: 500
description: Specify a minimum number of characters per chunk.
maxCharacters:
type: integer
default: 10000
description: Specify a maximum number of characters per chunk.
description: Additional options for the chunking strategy.
title: ParseConfigChunkingStrategyOptions
ParseConfigChunkingStrategy:
type: object
properties:
type:
$ref: '#/components/schemas/ParseConfigChunkingStrategyType'
default: page
description: >
The type of chunking strategy. Supported values:
* `page`: Chunk document by pages.
* `document`: Entire document is a single chunk. Essentially no
chunking.
* `section`: Split by logical sections. Not supported for
target=spatial.
options:
$ref: '#/components/schemas/ParseConfigChunkingStrategyOptions'
description: Additional options for the chunking strategy.
description: Strategy for dividing the document into chunks.
title: ParseConfigChunkingStrategy
ParseConfigEngine:
type: string
enum:
- parse_performance
- parse_light
default: parse_performance
description: >
The parsing engine to use. Supported values:
* `parse_performance`: Full-featured parsing engine with highest
accuracy (default)
* `parse_light`: Lightweight parsing engine optimized for high-volume,
cost-sensitive ingestion. Uses the new layout model with full layout
support and the markdown target at lower cost and latency, but performs
worse than `parse_performance` on lower-quality scans, harder
handwriting, larger tables, non-Latin-based languages, and dense
checkbox regions.
title: ParseConfigEngine
ParseConfigBlockOptionsFigures:
type: object
properties:
enabled:
type: boolean
default: true
description: Whether to include figures in the output.
figureImageClippingEnabled:
type: boolean
default: true
description: Whether to clip and extract images from figures.
advancedChartExtractionEnabled:
type: boolean
default: false
description: >-
Whether to enable advanced chart extraction using vision models for
improved data extraction from charts.
customInstructions:
type: string
description: >
Custom instructions injected into the vision model prompt used to
analyze and summarize figures. Use to steer figure descriptions
toward your use case (e.g. domain terminology, details to always
capture). Requires `enabled: true`. Available on `parse_performance`
>= `2.0.0` and `parse_light` >= `1.0.0`.
description: Options for figure blocks.
title: ParseConfigBlockOptionsFigures
ParseConfigBlockOptionsTablesTargetFormat:
type: string
enum:
- markdown
- html
default: html
description: |
The target format for the table blocks. Supported values:
* `markdown`: Convert table to Markdown format
* `html`: Convert table to HTML format
title: ParseConfigBlockOptionsTablesTargetFormat
ParseConfigBlockOptionsTablesAgentic:
type: object
properties:
enabled:
type: boolean
default: false
description: Whether to enable agentic table processing.
customInstructions:
type: string
description: Custom instructions to guide the agentic table processing.
description: >-
Options for agentic table processing using VLM-based review and
correction.
title: ParseConfigBlockOptionsTablesAgentic
ParseConfigBlockOptionsTables:
type: object
properties:
enabled:
type: boolean
default: true
description: >-
This option is deprecated and will have no effect. It will be
removed in the next API version.
targetFormat:
$ref: '#/components/schemas/ParseConfigBlockOptionsTablesTargetFormat'
default: html
description: |
The target format for the table blocks. Supported values:
* `markdown`: Convert table to Markdown format
* `html`: Convert table to HTML format
tableHeaderContinuationEnabled:
type: boolean
default: false
description: >-
Whether to automatically copy table headers to headerless tables on
subsequent pages when they have matching column counts. Useful for
multi-page tables.
cellBlocksEnabled:
type: boolean
default: false
description: >-
Whether to include individual table cell blocks in the output. When
enabled, each cell in a table will be represented as a separate
block with its own bounding box and content and will be `children`
of the table block.
agentic:
$ref: '#/components/schemas/ParseConfigBlockOptionsTablesAgentic'
description: >-
Options for agentic table processing using VLM-based review and
correction.
description: Options for table blocks.
title: ParseConfigBlockOptionsTables
ParseConfigBlockOptionsTextAgentic:
type: object
properties:
enabled:
type: boolean
default: false
description: Whether to enable agentic text processing for OCR corrections.
customInstructions:
type: string
description: Custom instructions to guide the agentic text processing.
description: >-
Options for agentic text processing using VLM-based review and
correction.
title: ParseConfigBlockOptionsTextAgentic
ParseConfigBlockOptionsText:
type: object
properties:
signatureDetectionEnabled:
type: boolean
default: false
description: >-
Whether an additional vision model will be utilized for advanced
signature detection. Recommended for most use cases, but should be
disabled if signature detection is not necessary and latency is a
concern.
agentic:
$ref: '#/components/schemas/ParseConfigBlockOptionsTextAgentic'
description: >-
Options for agentic text processing using VLM-based review and
correction.
description: Options for text blocks.
title: ParseConfigBlockOptionsText
ParseConfigBlockOptionsKeyValue:
type: object
properties:
blankFieldFormattingEnabled:
type: boolean
default: false
description: >-
Whether to preserve blank field formatting for key-value pairs with
empty values.
description: Options for key-value pair blocks.
title: ParseConfigBlockOptionsKeyValue
ParseConfigBlockOptionsBarcodes:
type: object
properties:
imageClippingEnabled:
type: boolean
default: false
description: >-
Whether to clip and extract images of barcodes. When enabled,
barcode images will be available in the `imageUrl` field of
BarcodeDetails.
readingEnabled:
type: boolean
default: false
description: >-
Whether to decode and read barcode values. When enabled, decoded
values will be available in the `decodedValue` field of
BarcodeDetails.
description: Options for barcode blocks.
title: ParseConfigBlockOptionsBarcodes
ParseConfigBlockOptionsFormulas:
type: object
properties:
enabled:
type: boolean
default: false
description: >-
Whether to enable formula detection and parsing. When enabled,
mathematical formulas and equations are detected and their LaTeX
representations are included in the output. When disabled, formulas
will be detected as text blocks and may not be accurately parsed.
description: Options for formula blocks.
title: ParseConfigBlockOptionsFormulas
ParseConfigBlockOptions:
type: object
properties:
figures:
$ref: '#/components/schemas/ParseConfigBlockOptionsFigures'
description: Options for figure blocks.
tables:
$ref: '#/components/schemas/ParseConfigBlockOptionsTables'
description: Options for table blocks.
text:
$ref: '#/components/schemas/ParseConfigBlockOptionsText'
description: Options for text blocks.
keyValue:
$ref: '#/components/schemas/ParseConfigBlockOptionsKeyValue'
description: Options for key-value pair blocks.
barcodes:
$ref: '#/components/schemas/ParseConfigBlockOptionsBarcodes'
description: Options for barcode blocks.
formulas:
$ref: '#/components/schemas/ParseConfigBlockOptionsFormulas'
description: Options for formula blocks.
description: Options for controlling how different block types are processed.
title: ParseConfigBlockOptions
ParseConfigAdvancedOptionsExcelParsingMode:
type: string
enum:
- basic
- advanced
description: |
Controls how Excel files are parsed.
* `basic`: Fast, deterministic parsing.
* `advanced`: Enable layout block detection for complex spreadsheets.
For `.xls` files, `basic` mode is always used.
title: ParseConfigAdvancedOptionsExcelParsingMode
ParseConfigAdvancedOptionsReturnOcr:
type: object
properties:
words:
type: boolean
default: false
description: >-
Whether to include word-level OCR data in the response, including
word bounding boxes and confidence scores. This meaningfully impacts
the response size, consider using the signed url return format.
description: Options for returning raw OCR data in the response.
title: ParseConfigAdvancedOptionsReturnOcr
ParseConfigAdvancedOptionsEnrichmentFormat:
type: string
enum:
- xml
- bracket
default: xml
description: >
The format used for enrichment annotations in the output.
* `xml`: Use XML-style tags for enrichment annotations, e.g.
1 or 1234567890
* `bracket`: Use bracket-style notation for enrichment annotations, e.g.
[page_number: 1] or [barcode: 1234567890]
title: ParseConfigAdvancedOptionsEnrichmentFormat
ParseConfigAdvancedOptionsImageConversionQuality:
type: string
enum:
- high
- medium
- low
default: medium
description: >
Controls the quality level when converting images or documents to PDF
for parsing.
* `high`: Maximum quality, can add some latency for large/dense
documents
* `medium`: Balanced quality and speed
* `low`: Lower quality, smaller file sizes, faster processing
title: ParseConfigAdvancedOptionsImageConversionQuality
ParseConfigAdvancedOptionsFormattingDetectionItemsType:
type: string
enum:
- change_tracking
description: >
The type of formatting detection to enable.
* `"change_tracking"` — Detect tracked changes (insertions, deletions,
substitutions) indicated by strikethroughs, colored text, or underlines
in the source document.
title: ParseConfigAdvancedOptionsFormattingDetectionItemsType
ParseConfigAdvancedOptionsFormattingDetectionItems:
type: object
properties:
type:
$ref: >-
#/components/schemas/ParseConfigAdvancedOptionsFormattingDetectionItemsType
description: >
The type of formatting detection to enable.
* `"change_tracking"` — Detect tracked changes (insertions,
deletions, substitutions) indicated by strikethroughs, colored text,
or underlines in the source document.
required:
- type
title: ParseConfigAdvancedOptionsFormattingDetectionItems
ParseConfigAdvancedOptions:
type: object
properties:
pageRotationEnabled:
type: boolean
default: true
description: Whether to automatically detect and correct page rotation.
pageRanges:
$ref: '#/components/schemas/PageRanges'
excelParsingMode:
$ref: '#/components/schemas/ParseConfigAdvancedOptionsExcelParsingMode'
description: >
Controls how Excel files are parsed.
* `basic`: Fast, deterministic parsing.
* `advanced`: Enable layout block detection for complex
spreadsheets.
For `.xls` files, `basic` mode is always used.
excelSkipHiddenContent:
type: boolean
default: false
description: >-
Whether to exclude hidden rows, columns, and sheets when parsing
Excel files.
excelUseRawCellValues:
type: boolean
default: false
description: >-
Whether to return raw calculated cell values instead of
locale-formatted values when parsing Excel files. Useful when
downstream processing needs the underlying numeric or unformatted
data.
excelSkipCalculation:
type: boolean
default: true
description: >-
Whether to skip formula recalculation when opening Excel workbooks.
Significantly improves parsing speed for formula-heavy spreadsheets.
Disable if cell values depend on volatile functions like NOW() or
TODAY().
verticalGroupingThreshold:
type: number
format: double
default: 1
description: >-
Multiplier for the Y-axis threshold used to determine if text blocks
should be placed on the same line or not (0.1-5.0, default 1.0).
Higher values group elements that are further apart vertically. Only
applies when the spatial target is set.
returnOcr:
$ref: '#/components/schemas/ParseConfigAdvancedOptionsReturnOcr'
description: Options for returning raw OCR data in the response.
alwaysConvertToPdf:
type: boolean
default: false
description: >-
Whether to convert supported file types (images, Word documents,
PowerPoint, Excel, HTML) to PDF before parsing. This can improve
parsing quality for some file types and ensures spatial output with
bounding boxes.
enrichmentFormat:
$ref: '#/components/schemas/ParseConfigAdvancedOptionsEnrichmentFormat'
default: xml
description: >
The format used for enrichment annotations in the output.
* `xml`: Use XML-style tags for enrichment annotations, e.g.
1 or 1234567890
* `bracket`: Use bracket-style notation for enrichment annotations,
e.g. [page_number: 1] or [barcode: 1234567890]
imageConversionQuality:
$ref: >-
#/components/schemas/ParseConfigAdvancedOptionsImageConversionQuality
default: medium
description: >
Controls the quality level when converting images or documents to
PDF for parsing.
* `high`: Maximum quality, can add some latency for large/dense
documents
* `medium`: Balanced quality and speed
* `low`: Lower quality, smaller file sizes, faster processing
formattingDetection:
type: array
items:
$ref: >-
#/components/schemas/ParseConfigAdvancedOptionsFormattingDetectionItems
description: >
Enable detection of formatting-based annotations in the document.
Currently supports change tracking detection.
When enabled, detected changes are represented inline within the
`content` field of applicable blocks using standard HTML
change-tracking elements:
[``](https://developer.mozilla.org/en-US/docs/Web/HTML/Element/ins)
for insertions and
[``](https://developer.mozilla.org/en-US/docs/Web/HTML/Element/del)
for deletions, grouped inside a `` wrapper.
Affected block types: `text`, `heading`, `section_heading`,
`header`, `footer`.
**Note:** Requires `engine: "parse_performance"` with `engineVersion
>= "2.0.0"`.
title: ParseConfigAdvancedOptions
ParseConfig:
type: object
properties:
target:
$ref: '#/components/schemas/ParseConfigTarget'
default: markdown
description: >
The target format for the parsed content.
Supported values:
* `markdown`: True markdown with logical reading order (headings,
lists, tables, checkboxes). Best default for LLMs/RAG and enables
section-based chunking.
* `spatial`: Layout/position-preserving text that uses markdown
elements for block types but is not strictly markdown due to
whitespace/tabs used to maintain placement. Only page-based chunking
is supported.
Guidance:
* Prefer `markdown` for most documents, multi-column reading order,
and retrieval use cases
* Prefer `spatial` for messy/scanned/handwritten or skewed
documents, when you need near 1:1 layout fidelity, or for BOL-like
logistics docs
See “Markdown vs Spatial” in the [Parse
guide](https://docs.extend.ai/2026-02-09/parsing/configuration#target-format)
for details.
chunkingStrategy:
$ref: '#/components/schemas/ParseConfigChunkingStrategy'
description: Strategy for dividing the document into chunks.
engine:
$ref: '#/components/schemas/ParseConfigEngine'
default: parse_performance
description: >
The parsing engine to use. Supported values:
* `parse_performance`: Full-featured parsing engine with highest
accuracy (default)
* `parse_light`: Lightweight parsing engine optimized for
high-volume, cost-sensitive ingestion. Uses the new layout model
with full layout support and the markdown target at lower cost and
latency, but performs worse than `parse_performance` on
lower-quality scans, harder handwriting, larger tables,
non-Latin-based languages, and dense checkbox regions.
engineVersion:
type: string
default: latest
description: >
Pin a specific parser engine version for reproducibility. When set
to `latest`, the most recent stable version of the selected engine
is used.
blockOptions:
$ref: '#/components/schemas/ParseConfigBlockOptions'
description: Options for controlling how different block types are processed.
advancedOptions:
$ref: '#/components/schemas/ParseConfigAdvancedOptions'
description: >-
Configuration options for the parsing process. Defaults depend on the
selected parser engine and version.
title: ParseConfig
SplitConfig:
type: object
properties:
baseProcessor:
$ref: '#/components/schemas/SplitBaseProcessor'
default: splitting_performance
baseVersion:
type: string
description: >-
The version of the `"splitting_performance"` or `"splitting_light"`
processor to use. If not provided, the latest stable version for the
selected `baseProcessor` will be used automatically. See [Splitting
Changelog](https://docs.extend.ai/2026-02-09/model-versioning/splitting/splitting-performance)
for more details.
splitClassifications:
$ref: '#/components/schemas/SplitClassifications'
splitRules:
type: string
description: >-
Custom rules to guide the document splitting process in natural
language.
advancedOptions:
$ref: '#/components/schemas/SplitAdvancedOptions'
description: Advanced configuration options.
parseConfig:
$ref: '#/components/schemas/ParseConfig'
description: Configuration options for the parsing process.
required:
- splitClassifications
title: SplitConfig
SplitterVersion:
type: object
properties:
object:
$ref: '#/components/schemas/SplitterVersionObject'
description: The type of object. Will always be `"splitter_version"`.
id:
type: string
description: |
The unique identifier for this version of the splitter.
Example: `"splv_xK9mLPqRtN3vS8wF5hB2cQ"`
description:
type:
- string
- 'null'
description: |
A description of this version of the splitter.
Example: `"Updated split rules for multi-invoice packets"`
version:
type: string
description: >
The version number or identifier for this specific version of the
splitter. The draft version will have version="draft".
Examples: `"1.0"`, `"2.1"`, `"draft"`
config:
$ref: '#/components/schemas/SplitConfig'
description: |
The configuration settings for this version of the splitter.
splitterId:
type: string
description: |
The ID of the splitter that this version belongs to.
Example: `"spl_Xj8mK2pL9nR4vT7qY5wZ"`
createdAt:
$ref: '#/components/schemas/CreatedAt'
required:
- object
- id
- description
- version
- config
- splitterId
- createdAt
title: SplitterVersion
Splitter:
type: object
properties:
object:
$ref: '#/components/schemas/SplitterObject'
description: The type of object. Will always be `"splitter"`.
id:
type: string
description: |
The ID of the splitter.
Example: `"spl_Xj8mK2pL9nR4vT7qY5wZ"`
name:
type: string
description: |
The name of the splitter.
Example: `"Invoice Packet Splitter"`
createdAt:
$ref: '#/components/schemas/CreatedAt'
updatedAt:
$ref: '#/components/schemas/UpdatedAt'
draftVersion:
$ref: '#/components/schemas/SplitterVersion'
description: >-
The draft version of the splitter. This is the editable version in
the Extend dashboard.
required:
- object
- id
- name
- createdAt
- updatedAt
- draftVersion
title: Splitter
ApiError:
type: object
properties:
code:
type: string
description: Error code for programmatic handling.
message:
type: string
description: |
Human-readable error message suitable for displaying to developers.
Do not rely on the exact text of this message as it may change.
retryable:
type: boolean
description: >
Whether the request can be retried. When true, retry with
exponential backoff.
When false, fix the underlying issue before retrying.
requestId:
type: string
description: |
Unique request identifier for support purposes. Always include this
when contacting Extend support about an error.
required:
- code
- message
- retryable
description: >
Standard error response format for all Extend API errors.
See the [Error Codes
documentation](https://docs.extend.ai/2026-02-09/api-reference/error-handling)
for error handling recommendations.
title: ApiError
securitySchemes:
BearerAuth:
type: http
scheme: bearer
```
## Examples
**Response**
```json
{
"object": "splitter",
"id": "spl_Xj8mK2pL9nR4vT7qY5wZ",
"name": "Invoice Packet Splitter",
"createdAt": "2024-03-21T16:45:00Z",
"updatedAt": "2024-03-21T16:45:00Z",
"draftVersion": {
"object": "splitter_version",
"id": "splv_xK9mLPqRtN3vS8wF5hB2cQ",
"description": "Updated split rules for multi-invoice packets",
"version": "draft",
"config": {
"splitClassifications": [
{
"id": "my_unique_id",
"type": "invoice",
"description": "An invoice is a document that lists the items purchased and the total amount due.",
"identifierKey": "Extract the invoice number from the document header"
}
],
"baseProcessor": "splitting_performance",
"baseVersion": "string",
"splitRules": "string",
"advancedOptions": {
"splitExcelDocumentsBySheetEnabled": false,
"pageRanges": [
{
"start": 1,
"end": 10
},
{
"start": 20,
"end": 30
}
],
"pageOverlapEnabled": false,
"splitIdentifierRules": "string",
"splitMethod": "high_precision"
},
"parseConfig": {
"target": "markdown",
"chunkingStrategy": {
"type": "page",
"options": {
"minCharacters": 500,
"maxCharacters": 10000
}
},
"engine": "parse_performance",
"engineVersion": "latest",
"blockOptions": {
"figures": {
"enabled": true,
"figureImageClippingEnabled": true,
"advancedChartExtractionEnabled": false,
"customInstructions": "string"
},
"tables": {
"targetFormat": "html",
"tableHeaderContinuationEnabled": false,
"cellBlocksEnabled": false,
"agentic": {
"enabled": false,
"customInstructions": "string"
},
"enabled": true
},
"text": {
"signatureDetectionEnabled": false,
"agentic": {
"enabled": false,
"customInstructions": "string"
}
},
"keyValue": {
"blankFieldFormattingEnabled": false
},
"barcodes": {
"imageClippingEnabled": false,
"readingEnabled": false
},
"formulas": {
"enabled": false
}
},
"advancedOptions": {
"pageRotationEnabled": true,
"pageRanges": [
{
"start": 1,
"end": 10
},
{
"start": 20,
"end": 30
}
],
"excelParsingMode": "basic",
"excelSkipHiddenContent": false,
"excelUseRawCellValues": false,
"excelSkipCalculation": true,
"verticalGroupingThreshold": 1,
"returnOcr": {
"words": false
},
"alwaysConvertToPdf": false,
"enrichmentFormat": "xml",
"imageConversionQuality": "medium",
"formattingDetection": [
{
"type": "change_tracking"
}
]
}
}
},
"splitterId": "spl_Xj8mK2pL9nR4vT7qY5wZ",
"createdAt": "2024-03-21T16:45:00Z"
}
}
```
**SDK Code**
```typescript
import { ExtendClient } from "extend-ai";
async function main() {
const client = new ExtendClient({
token: "YOUR_TOKEN_HERE",
extendApiVersion: "2026-02-09",
});
await client.splitters.retrieve("splitter_id_here", {});
}
main();
```
```python
from extend_ai import Extend
client = Extend(
token="YOUR_TOKEN_HERE",
extend_api_version="2026-02-09",
)
client.splitters.retrieve(
id="splitter_id_here",
)
```
```java
package com.example.usage;
import ai.extend.ExtendClientBase;
import ai.extend.resources.splitters.requests.SplittersRetrieveRequest;
public class Example {
public static void main(String[] args) {
ExtendClientBase client = ExtendClientBase
.builder()
.token("YOUR_TOKEN_HERE")
.extendApiVersion("2026-02-09")
.build();
client.splitters().retrieve(
"splitter_id_here",
SplittersRetrieveRequest
.builder()
.build()
);
}
}
```
```go
package example
import (
context "context"
extend "github.com/extend-hq/extend-go-sdk"
client "github.com/extend-hq/extend-go-sdk/client"
option "github.com/extend-hq/extend-go-sdk/option"
)
func do() {
client := client.NewClient(
option.WithToken(
"YOUR_TOKEN_HERE",
),
)
request := &extend.SplittersRetrieveRequest{}
client.Splitters.Retrieve(
context.TODO(),
"splitter_id_here",
request,
)
}
```