> This page is for version v2026-02-09 (default).
> For other versions, use one of these documentation indexes:
> - v2026-02-09 (default): https://docs.extend.ai/2026-02-09/llms.txt
> - v2025-04-21: https://docs.extend.ai/2025-04-21/llms.txt
> - v2024-12-23: https://docs.extend.ai/2024-12-23/llms.txt

> ## 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.
>
> ## API version
> The current API version is `2026-02-09`, served at the site root (no version prefix in URLs).
> If this page URL contains `/2025-04-21/` or `/2024-12-23/`, you are reading an older API version.
> Prefer the current docs at https://docs.extend.ai/llms.txt unless the user explicitly needs that older version.
> Do not treat older-version pages as the source of truth for new integrations.

# Extractor Deleted

POST 

Reference: https://docs.extend.ai/api-reference/webhook-events/extract/extractor-deleted-webhook

## Request

### Payload

- `eventId` (string, required) — Unique identifier for the event
- `payload` (Extractor, required)

## Types

### Extractor

- `object` (enum, required) — The type of object. Will always be `"extractor"`.
  - Allowed values: `extractor`
- `id` (string, required) — The ID of the extractor. Example: `"ex_Xj8mK2pL9nR4vT7qY5wZ"`
- `name` (string, required) — The name of the extractor. Example: `"Invoice Extractor"`
- `createdAt` (string, required) — The time (in UTC) at which the object was created. Will follow the RFC 3339 format. Example: `"2024-03-21T16:45:00Z"`
- `updatedAt` (string, required) — The time (in UTC) at which the object was last updated. Will follow the RFC 3339 format. Example: `"2024-03-21T16:45:00Z"`
- `draftVersion` (ExtractorVersion, required) — The draft version of the extractor. This is the editable version in the Extend dashboard.

### ExtractorVersion

- `object` (enum, required) — The type of object. Will always be `"extractor_version"`.
  - Allowed values: `extractor_version`
- `id` (string, required) — The unique identifier for this version of the extractor. Example: `"exv_xK9mLPqRtN3vS8wF5hB2cQ"`
- `description` (string, required, nullable) — A description of this version of the extractor. Example: `"Updated extraction fields for new invoice format"`
- `version` (string, required) — The version number or identifier for this specific version of the extractor. The draft version will have version="draft". Examples: `"1.0"`, `"2.1"`, `"draft"`
- `config` (ExtractConfig, required) — The configuration settings for this version of the extractor. This is a union of two possible shapes: - **[JSON Schema config](https://docs.extend.ai/2026-02-09/extraction/schema):** The current config format. All extractors created through this API version use this shape. - **[Legacy config](https://docs.extend.ai/2025-04-21/product/legacy/legacy-schema):** A fields-array config from a previous API version. This shape is only returned for extractors that were originally configured with the legacy format. This API version does not support creating extractors with legacy configs.
- `extractorId` (string, required) — The ID of the extractor that this version belongs to. Example: `"ex_Xj8mK2pL9nR4vT7qY5wZ"`
- `createdAt` (string, required) — The time (in UTC) at which the object was created. Will follow the RFC 3339 format. Example: `"2024-03-21T16:45:00Z"`
- `createdBy` (CreatedBy, required) — The actor that created this resource. * `user` — the resource was created via the studio by a logged-in user. The user's `email` is exposed. * `api_key` — the resource was created via the API using an API key. The key's `name` is exposed. May be `null` for resources created before attribution.

### ExtractConfig

### CreatedBy

The actor that created this resource. * `user` — the resource was created via the studio by a logged-in user. The user's `email` is exposed. * `api_key` — the resource was created via the API using an API key. The key's `name` is exposed. May be `null` for resources created before attribution.

- `type`: `user` (user)
  - `email` (string, required) — The email address of the user who created the resource.
- `type`: `api_key` (api_key)
  - `name` (string, required) — The name of the API key that created the resource.

### ExtractConfigJson

- `baseProcessor` (enum, optional, default: extraction_performance) — The base processor to use. For extractors, this can be `"extraction_performance"`, `"extraction_light"`, or `"extraction_operator"`. Defaults to `"extraction_performance"` if not provided. See [Extraction Changelog](https://docs.extend.ai/2026-02-09/model-versioning/extraction/extraction-performance) for more details. `"extraction_operator"` selects [Operator](https://docs.extend.ai/2026-02-09/extraction/operator).
  - Allowed values: `extraction_performance`, `extraction_light`, `extraction_operator`
- `baseVersion` (string, optional) — The version of the `"extraction_performance"`, `"extraction_light"`, or `"extraction_operator"` processor to use. If not provided, the latest stable version will be used. See [Extraction Changelog](https://docs.extend.ai/2026-02-09/model-versioning/extraction/extraction-performance) for more details.
- `extractionRules` (string, optional) — Custom rules to guide the extraction process in natural language. When `schema` is omitted, `extractionRules` also serves as schema generation instructions — for example, `"Invoice with vendor name, line items, and total due"`. Providing focused instructions produces a more targeted inferred schema.
- `schema` (map from string to any, optional) — JSON Schema definition of the data to extract. **Optional** — if omitted, Extend automatically infers a schema from the document before running extraction. No extractor is required. See the [JSON Schema guide](https://docs.extend.ai/2026-02-09/extraction/schema) for details and examples of schema configuration.
- `advancedOptions` (ExtractAdvancedOptions, optional) — Advanced configuration options.
- `parseConfig` (ParseConfig, optional) — Configuration options for the parsing process.

### ExtractConfigLegacy

- `fields` (list of ExtractionField, required) — Array of fields to extract from the document. This is the legacy format. We recommend using JSON Schema (`schema` property) for new implementations.
- `baseProcessor` (enum, optional, default: extraction_performance) — The base processor to use. For extractors, this can be `"extraction_performance"` or `"extraction_light"`. Defaults to `"extraction_performance"` if not provided. See [Extraction Changelog](https://docs.extend.ai/2026-02-09/model-versioning/extraction/extraction-performance) for more details. `"extraction_operator"` is not supported on legacy `fields` configs.
  - Allowed values: `extraction_performance`, `extraction_light`
- `baseVersion` (string, optional) — The version of the `"extraction_performance"` or `"extraction_light"` processor to use. If not provided, the latest stable version will be used. See [Extraction Changelog](https://docs.extend.ai/2026-02-09/model-versioning/extraction/extraction-performance) for more details.
- `extractionRules` (string, optional) — Custom rules to guide the extraction process in natural language.
- `advancedOptions` (ExtractAdvancedOptions, optional) — Advanced configuration options.
- `parseConfig` (ParseConfig, optional) — Configuration options for the parsing process.

### ExtractAdvancedOptions

- `modelReasoningInsightsEnabled` (boolean, optional) — Whether to enable model reasoning insights.
- `advancedMultimodalEnabled` (boolean, optional) — Whether to enable advanced multimodal features.
- `citationsEnabled` (boolean, optional) — Whether to enable citations in the output.
- `citationMode` (enum, optional, default: line) — Controls the granularity of citations returned alongside extracted values. Requires `citationsEnabled=true` and a base processor version that supports bounding box citations. - `line`: Use OCR lines for citations. This can return one or more relevant OCR lines for each citation. This is the default mode. - `word`: Narrow each matched citation down to the relevant OCR word span when possible. Note: this might still return line citations in cases where the citation model is unable to reliably narrow down to a word-level citation. Typically, this only makes sense when you are doing array extraction and want precise word citations from a given cell in a table to match an array property, e.g. `line_items.total`. - `block`: Use parser blocks (e.g. full paragraphs, key-val regions, tables, lists, etc.) and return block-level polygons for each citation. Will have highest recall in terms of overlap with the extracted value source, but least granularity.
  - Allowed values: `line`, `word`, `block`
- `arrayCitationStrategy` (enum, optional) — Granularity for array citations. Requires turning on citations: `citationsEnabled=true`. - `item`: Creates item-level citations for array fields. This will return a single bbox citation for each "item" in the array e.g. line_items[0], line_items[1], etc. - `property`: Creates property-level citations (cell-level citations) for array fields. This will return a citation for each property/cell for every item/row in the array, e.g. line_items[0].description, line_items[1].price, etc.
  - Allowed values: `item`, `property`
- `arrayStrategy` (ArrayStrategy, optional) — Strategy for handling large arrays in documents.
- `chunkingOptions` (ExtractChunkingOptions, optional) — Options controlling how documents are chunked before extraction.
- `excelSheetRanges` (list of ExcelSheetRange, optional) — Ranges of sheet indices to extract from Excel documents.
- `excelSheetSelectionStrategy` (enum, optional) — Strategy for selecting sheets from Excel documents.
  - Allowed values: `intelligent`, `all`, `first`, `last`
- `pageRanges` (list of PageRangesItems, optional) — Limit processing to the specified page ranges. See [Page Ranges](https://docs.extend.ai/2026-02-09/page-ranges).
- `reviewAgent` (ExtractAdvancedOptionsReviewAgent, optional) — Configuration for the review agent that analyzes extraction results. When enabled, each field in the output metadata will include a `reviewAgentScore` (1-5) and may include additional `insights` of type `issue` or `review_summary` to help identify fields that may need manual review. Enabling the review agent incurs additional credits. To learn more, view the [Review Agent Documentation](https://docs.extend.ai/2026-02-09/extraction/review-agent)
- `currentDateEnabled` (boolean, optional) — Whether to include the current date as context for the model during extraction. Defaults to `false`.

### ParseConfig

Configuration options for the parsing process. Defaults depend on the selected parser engine and version.

- `target` (enum, optional, default: markdown) — 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.
  - Allowed values: `markdown`, `spatial`
- `chunkingStrategy` (ParseConfigChunkingStrategy, optional) — Strategy for dividing the document into chunks.
- `engine` (enum, optional, default: parse_performance) — 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. * `parse_auto`: Adaptive parsing that classifies difficulty and routes work per page — simple pages are parsed with the parse_light model pipeline while complex pages get performance-level model treatment. Billed per page by complexity.
  - Allowed values: `parse_performance`, `parse_light`, `parse_auto`
- `engineVersion` (string, optional, default: latest) — Pin a specific parser engine version for reproducibility. When set to `latest`, the most recent stable version of the selected engine is used.
- `blockOptions` (ParseConfigBlockOptions, optional) — Options for controlling how different block types are processed.
- `advancedOptions` (ParseConfigAdvancedOptions, optional)

### ExtractionField

- `id` (string, required) — Unique identifier for the field.
- `name` (string, required) — Human-readable name for the field.
- `type` (enum, required) — The type of the field.
  - Allowed values: `string`, `number`, `currency`, `boolean`, `date`, `array`, `enum`, `object`, `signature`
- `description` (string, required) — Detailed description of the field, including expected content and format.
- `schema` (list of ExtractionField, optional) — Required when type is "array" or "object". Contains nested field definitions.
- `enum` (list of Enum, optional) — Required when type is "enum". List of allowed values.

### ArrayStrategy

- `type` (enum, required) — The strategy type for handling large array use cases. For most use cases this should be left null, or should be set to `large_array_heuristics`. If you're unsure of what your use case needs, reach out to the Extend team for help. - `large_array_heuristics`: Optimized for documents with very large arrays, but where latency matters. This strategy uses specialized heuristics around chunking, tables, and merging to handle large arrays efficiently over large documents. - `large_array_max_context`: Optimizes for accuracy over latency in documents with very large arrays. This strategy will do multiple passes through the entire document to ensure there is no context loss across any chunks/pages, maximizing accuracy for complex array extraction, but adding material latency. This strategy incurs additional extraction credits when enabled. - `large_array_overlap_context`: Balances accuracy and latency in documents with very large arrays. This strategy will always maintain surrounding/overlapping page context for every chunk/page that is extracted, eliminating array failure modes from context loss across page boundaries.
  - Allowed values: `large_array_heuristics`, `large_array_max_context`, `large_array_overlap_context`

### ExtractChunkingOptions

Options controlling how documents are chunked before extraction.

- `chunkingStrategy` (enum, optional) — The strategy to use for chunking the document.
  - Allowed values: `standard`, `semantic`, `contextual`
- `pageChunkSize` (integer, optional) — The size of page chunks.
- `chunkSelectionStrategy` (enum, optional) — The strategy to use for selecting chunks.
  - Allowed values: `intelligent`, `confidence`, `take_first`, `take_last`
- `customSemanticChunkingRules` (string, optional) — Custom rules for semantic chunking.

### ExcelSheetRange

- `start` (integer, required) — The starting sheet index (0-based).
- `end` (integer, required) — The ending sheet index (0-based). Must be greater than or equal to start.

### PageRangesItems

- `start` (integer, required) — The start page of the range.
- `end` (integer, required, default: 750) — The end page of the range.

### ExtractAdvancedOptionsReviewAgent

Configuration for the review agent that analyzes extraction results. When enabled, each field in the output metadata will include a `reviewAgentScore` (1-5) and may include additional `insights` of type `issue` or `review_summary` to help identify fields that may need manual review. Enabling the review agent incurs additional credits. To learn more, view the [Review Agent Documentation](https://docs.extend.ai/2026-02-09/extraction/review-agent)

- `enabled` (boolean, optional) — Whether to enable the review agent.

### ParseConfigChunkingStrategy

Strategy for dividing the document into chunks.

- `type` (enum, optional, default: page) — 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.
  - Allowed values: `page`, `document`, `section`
- `options` (ParseConfigChunkingStrategyOptions, optional) — Additional options for the chunking strategy.

### ParseConfigBlockOptions

Options for controlling how different block types are processed.

- `figures` (ParseConfigBlockOptionsFigures, optional) — Options for figure blocks.
- `tables` (ParseConfigBlockOptionsTables, optional) — Options for table blocks.
- `text` (ParseConfigBlockOptionsText, optional) — Options for text blocks.
- `keyValue` (ParseConfigBlockOptionsKeyValue, optional) — Options for key-value pair blocks.
- `barcodes` (ParseConfigBlockOptionsBarcodes, optional) — Options for barcode blocks.
- `formulas` (ParseConfigBlockOptionsFormulas, optional) — Options for formula blocks.

### ParseConfigAdvancedOptions

- `pageRotationEnabled` (boolean, optional, default: true) — Whether to automatically detect and correct page rotation.
- `pageRanges` (list of PageRangesItems, optional) — Limit processing to the specified page ranges. See [Page Ranges](https://docs.extend.ai/2026-02-09/page-ranges).
- `excelParsingMode` (enum, optional) — Controls how Excel files are parsed. * `basic`: Fast, deterministic parsing. * `advanced`: Enable layout block detection for complex spreadsheets. This mode incurs additional credits when enabled. For `.xls` files, `basic` mode is always used.
  - Allowed values: `basic`, `advanced`
- `excelSkipHiddenContent` (boolean, optional, default: false) — Whether to exclude hidden rows, columns, and sheets when parsing Excel files.
- `excelUseRawCellValues` (boolean, optional, default: false) — 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` (boolean, optional, default: true) — 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().
- `excelIncludeCellMetadata` (boolean, optional, default: false) — Whether to include spreadsheet cell provenance when parsing Excel files in advanced mode. When enabled, table cell block details include source cell references and formulas, text or heading block details can include source ranges, and HTML table output includes `data-cell` and `data-formula` attributes.
- `excelIncludeCellFormatting` (boolean, optional, default: false) — Whether to include spreadsheet cell formatting when parsing Excel files in advanced mode. When enabled, table cell block details include structured formatting such as bold, italic, font color, and background color, and HTML table output preserves inline cell styles.
- `verticalGroupingThreshold` (double, optional, default: 1) — 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` (ParseConfigAdvancedOptionsReturnOcr, optional) — Options for returning raw OCR data in the response.
- `alwaysConvertToPdf` (boolean, optional, default: false) — 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` (enum, optional, default: xml) — 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]
  - Allowed values: `xml`, `bracket`
- `imageConversionQuality` (enum, optional, default: medium) — 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
  - Allowed values: `high`, `medium`, `low`
- `formattingDetection` (list of ParseConfigAdvancedOptionsFormattingDetectionItems, optional) — 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: [`<ins>`](https://developer.mozilla.org/en-US/docs/Web/HTML/Element/ins) for insertions and [`<del>`](https://developer.mozilla.org/en-US/docs/Web/HTML/Element/del) for deletions, grouped inside a `<change>` wrapper. Affected block types: `text`, `heading`, `section_heading`, `header`, `footer`. **Note:** Requires `engine: "parse_performance"` with `engineVersion >= "2.0.0"`.

### Enum

- `value` (string, required) — The value of the enum option.
- `description` (string, required) — Description of what this enum value represents.

### ParseConfigChunkingStrategyOptions

Additional options for the chunking strategy.

- `minCharacters` (integer, optional, default: 500) — Specify a minimum number of characters per chunk.
- `maxCharacters` (integer, optional, default: 10000) — Specify a maximum number of characters per chunk.

### ParseConfigBlockOptionsFigures

Options for figure blocks.

- `enabled` (boolean, optional, default: true) — Whether to include figures in the output.
- `figureImageClippingEnabled` (boolean, optional, default: true) — Whether to clip and extract images from figures.
- `advancedChartExtractionEnabled` (boolean, optional, default: false) — Whether to enable advanced chart extraction using vision models for improved data extraction from charts.
- `customInstructions` (string, optional) — 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`.

### ParseConfigBlockOptionsTables

Options for table blocks.

- `targetFormat` (enum, optional, default: html) — The target format for the table blocks. Supported values: * `markdown`: Convert table to Markdown format * `html`: Convert table to HTML format
  - Allowed values: `markdown`, `html`
- `tableHeaderContinuationEnabled` (boolean, optional, default: false) — Whether to automatically copy table headers to headerless tables on subsequent pages when they have matching column counts. Useful for multi-page tables.
- `cellBlocksEnabled` (boolean, optional, default: false) — 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. Only supported on `parse_performance` engineVersion `1.0.1`.
- `agentic` (ParseConfigBlockOptionsTablesAgentic, optional) — Options for agentic table processing using VLM-based review and correction. Enabling this incurs additional credits on pages where agentic table correction is triggered.
- `enabled` (boolean, optional, default: true, deprecated) — This option is deprecated and will have no effect. It will be removed in the next API version.

### ParseConfigBlockOptionsText

Options for text blocks.

- `signatureDetectionEnabled` (boolean, optional, default: false) — 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` (ParseConfigBlockOptionsTextAgentic, optional) — Options for agentic text processing using VLM-based review and correction. Enabling this incurs additional credits on pages where agentic text correction is triggered.

### ParseConfigBlockOptionsKeyValue

Options for key-value pair blocks.

- `blankFieldFormattingEnabled` (boolean, optional, default: false) — Whether to preserve blank field formatting for key-value pairs with empty values.

### ParseConfigBlockOptionsBarcodes

Options for barcode blocks.

- `imageClippingEnabled` (boolean, optional, default: false) — Whether to clip and extract images of barcodes. When enabled, barcode images will be available in the `imageUrl` field of BarcodeDetails.
- `readingEnabled` (boolean, optional, default: false) — Whether to decode and read barcode values. When enabled, decoded values will be available in the `decodedValue` field of BarcodeDetails.

### ParseConfigBlockOptionsFormulas

Options for formula blocks.

- `enabled` (boolean, optional, default: false) — 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.

### ParseConfigAdvancedOptionsReturnOcr

Options for returning raw OCR data in the response.

- `words` (boolean, optional, default: false) — 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.

### ParseConfigAdvancedOptionsFormattingDetectionItems

- `type` (enum, required) — 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.
  - Allowed values: `change_tracking`

### ParseConfigBlockOptionsTablesAgentic

Options for agentic table processing using VLM-based review and correction. Enabling this incurs additional credits on pages where agentic table correction is triggered.

- `enabled` (boolean, optional, default: false) — Whether to enable agentic table processing.
- `customInstructions` (string, optional) — Custom instructions to guide the agentic table processing.

### ParseConfigBlockOptionsTextAgentic

Options for agentic text processing using VLM-based review and correction. Enabling this incurs additional credits on pages where agentic text correction is triggered.

- `enabled` (boolean, optional, default: false) — Whether to enable agentic text processing for OCR corrections.
- `customInstructions` (string, optional) — Custom instructions to guide the agentic text processing.