openapi: 3.0.3
info:
  title: Llama Platform Agent Data Configurations API
  version: 0.1.0
tags:
- name: Configurations
paths:
  /api/v1/beta/configurations:
    post:
      tags:
      - Configurations
      summary: Create Configuration
      description: Upsert a product configuration; updates if one with the same name + product type + project exists, otherwise creates.
      operationId: create_configuration_api_v1_beta_configurations_post
      security:
      - HTTPBearer: []
      parameters:
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Project Id
      - name: organization_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Organization Id
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ConfigurationCreateRequest'
      responses:
        '201':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ConfigurationResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    get:
      tags:
      - Configurations
      summary: List Configurations
      description: List product configurations for the current project.
      operationId: list_configurations_api_v1_beta_configurations_get
      security:
      - HTTPBearer: []
      parameters:
      - name: product_type
        in: query
        required: false
        schema:
          anyOf:
          - type: array
            items:
              enum:
              - split_v1
              - extract_v2
              - classify_v2
              - parse_v2
              - spreadsheet_v1
              - unknown
              type: string
          - type: 'null'
          description: Filter by one or more product types. Repeat the parameter for multiple values.
          title: Product Type
        description: Filter by one or more product types. Repeat the parameter for multiple values.
      - name: name
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Filter by configuration name.
          title: Name
        description: Filter by configuration name.
      - name: page_size
        in: query
        required: false
        schema:
          anyOf:
          - type: integer
          - type: 'null'
          description: Number of items per page.
          title: Page Size
        description: Number of items per page.
      - name: page_token
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: Pagination token.
          title: Page Token
        description: Pagination token.
      - name: latest_only
        in: query
        required: false
        schema:
          type: boolean
          description: Return only the latest version per configuration name.
          default: false
          title: Latest Only
        description: Return only the latest version per configuration name.
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Project Id
      - name: organization_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Organization Id
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ConfigurationQueryResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/beta/configurations/{config_id}:
    get:
      tags:
      - Configurations
      summary: Get Configuration
      description: Get a single product configuration by ID.
      operationId: get_configuration_api_v1_beta_configurations__config_id__get
      security:
      - HTTPBearer: []
      parameters:
      - name: config_id
        in: path
        required: true
        schema:
          type: string
          title: Config Id
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Project Id
      - name: organization_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Organization Id
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ConfigurationResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    put:
      tags:
      - Configurations
      summary: Update Configuration
      description: Update an existing product configuration.
      operationId: update_configuration_api_v1_beta_configurations__config_id__put
      security:
      - HTTPBearer: []
      parameters:
      - name: config_id
        in: path
        required: true
        schema:
          type: string
          title: Config Id
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Project Id
      - name: organization_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Organization Id
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ConfigurationUpdateRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ConfigurationResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    delete:
      tags:
      - Configurations
      summary: Delete Configuration
      description: Delete a product configuration.
      operationId: delete_configuration_api_v1_beta_configurations__config_id__delete
      security:
      - HTTPBearer: []
      parameters:
      - name: config_id
        in: path
        required: true
        schema:
          type: string
          title: Config Id
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Project Id
      - name: organization_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: uuid
          - type: 'null'
          title: Organization Id
      - name: session
        in: cookie
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          title: Session
      responses:
        '204':
          description: Successful Response
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
components:
  schemas:
    ExtractV2Parameters:
      properties:
        target_pages:
          anyOf:
          - type: string
          - type: 'null'
          title: Target Pages
          description: Comma-separated page numbers or ranges to process (1-based). Omit to process all pages.
          examples:
          - 1,3,5-7
          - 1-3,8-10
        max_pages:
          anyOf:
          - type: integer
            minimum: 1.0
          - type: 'null'
          title: Max Pages
          description: Maximum number of pages to process. Omit for no limit.
          examples:
          - 10
        tier:
          type: string
          enum:
          - cost_effective
          - agentic
          title: Tier
          description: 'Extract tier: cost_effective (5 credits/page) or agentic (15 credits/page)'
          default: cost_effective
          examples:
          - cost_effective
          - agentic
        version:
          type: string
          title: Version
          description: 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.
          default: latest
          examples:
          - latest
        data_schema:
          additionalProperties:
            anyOf:
            - additionalProperties: true
              type: object
            - items: {}
              type: array
            - type: string
            - type: integer
            - type: number
            - type: boolean
            - type: 'null'
          type: object
          title: Data Schema
          description: JSON Schema defining the fields to extract. Validate with the /schema/validate endpoint first.
        extraction_target:
          type: string
          enum:
          - per_doc
          - per_page
          - per_table_row
          title: Extraction Target
          description: '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'
          default: per_doc
          examples:
          - per_doc
          - per_page
          - per_table_row
        system_prompt:
          anyOf:
          - type: string
          - type: 'null'
          title: System Prompt
          description: Custom system prompt to guide extraction behavior
          examples:
          - Extract all monetary values in USD. If a currency is not specified, assume USD.
        cite_sources:
          type: boolean
          title: Cite Sources
          description: Include citations in results
          default: false
        confidence_scores:
          type: boolean
          title: Confidence Scores
          description: Include confidence scores in results
          default: false
        parse_tier:
          anyOf:
          - type: string
          - type: 'null'
          title: Parse Tier
          description: Parse tier to use before extraction. Defaults to the extract tier if not specified.
          examples:
          - fast
          - cost_effective
        parse_config_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Parse Config Id
          description: Saved parse configuration ID to control how the document is parsed before extraction
          examples:
          - cfg-11111111-2222-3333-4444-555555555555
        product_type:
          type: string
          const: extract_v2
          title: Product Type
          description: Product type.
      type: object
      required:
      - data_schema
      - product_type
      title: ExtractV2Parameters
      description: Typed parameters for an *extract v2* product configuration.
    SplitV1Parameters:
      properties:
        categories:
          items:
            $ref: '#/components/schemas/SplitCategory'
          type: array
          maxItems: 50
          minItems: 1
          title: Categories
          description: Categories to split documents into.
        splitting_strategy:
          $ref: '#/components/schemas/SplitStrategy'
          description: Strategy for splitting documents.
        product_type:
          type: string
          const: split_v1
          title: Product Type
          description: Product type.
      type: object
      required:
      - categories
      - product_type
      title: SplitV1Parameters
      description: Typed parameters for a *split v1* product configuration.
    ClassifyV2Rule:
      properties:
        type:
          type: string
          maxLength: 50
          minLength: 1
          title: Type
          description: Document type to assign when rule matches
          examples:
          - invoice
          - receipt
          - contract
          - report
          - proposal
        description:
          type: string
          maxLength: 500
          minLength: 10
          title: Description
          description: Natural language criteria for matching this rule
          examples:
          - contains invoice number, line items, and total amount
          - purchase receipt with transaction info and merchant details
          - legal contract with terms, conditions, and signatures
      type: object
      required:
      - type
      - description
      title: ClassifyV2Rule
      description: A rule for classifying documents.
    UntypedParameters:
      properties:
        product_type:
          type: string
          const: unknown
          title: Product Type
          description: Product type.
      additionalProperties: true
      type: object
      required:
      - product_type
      title: UntypedParameters
      description: 'Catch-all for configurations without a dedicated typed schema.


        Accepts arbitrary JSON fields alongside ``product_type``.'
    LlamaParseSpatialTextOptions:
      properties:
        preserve_layout_alignment_across_pages:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Preserve Layout Alignment Across Pages
          description: Maintain consistent text column alignment across page boundaries. Automatically enabled for document-level parsing modes
        preserve_very_small_text:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Preserve Very Small Text
          description: Include text below the normal size threshold. Useful for footnotes, watermarks, or fine print that might otherwise be filtered out
        do_not_unroll_columns:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Do Not Unroll Columns
          description: Keep multi-column layouts intact instead of linearizing columns into sequential text. Automatically enabled for non-fast tiers
      additionalProperties: false
      type: object
      title: LlamaParseSpatialTextOptions
      description: 'Spatial text output options for preserving document layout.


        Spatial text maintains the visual positioning of text elements, useful for

        documents where layout conveys meaning (forms, tables, multi-column layouts).'
    LlamaParseProcessingControl:
      properties:
        timeouts:
          $ref: '#/components/schemas/LlamaParseTimeouts'
          description: Timeout settings for job execution. Increase for large or complex documents
        job_failure_conditions:
          $ref: '#/components/schemas/LlamaParseJobFailureConditions'
          description: Quality thresholds that determine when a job should fail vs complete with partial results
      additionalProperties: false
      type: object
      title: LlamaParseProcessingControl
      description: Job processing controls for timeouts and failure handling.
    LlamaParseFastOptions:
      properties: {}
      additionalProperties: false
      type: object
      title: LlamaParseFastOptions
      description: 'Options for fast tier parsing (rule-based, no AI).


        Fast tier uses deterministic algorithms for text extraction without AI enhancement.

        It''s the fastest and most cost-effective option, best suited for simple documents

        with standard layouts. Currently has no configurable options but reserved for

        future expansion.'
    LlamaParseInputOptions:
      properties:
        html:
          $ref: '#/components/schemas/LlamaParseHtmlOptions'
          description: HTML/web page parsing options (applies to .html, .htm files)
        pdf:
          $ref: '#/components/schemas/LlamaParsePdfOptions'
          description: PDF-specific parsing options (applies to .pdf files)
        spreadsheet:
          $ref: '#/components/schemas/LlamaParseSpreadsheetOptions'
          description: Spreadsheet parsing options (applies to .xlsx, .xls, .csv, .ods files)
        presentation:
          $ref: '#/components/schemas/LlamaParsePresentationOptions'
          description: Presentation parsing options (applies to .pptx, .ppt, .odp, .key files)
      additionalProperties: false
      type: object
      title: LlamaParseInputOptions
      description: 'Input format-specific parsing options.


        These options only apply when parsing documents of the corresponding format.

        LlamaParse automatically detects the input format based on file extension and content.'
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    LlamaParseTables:
      properties:
        compact_markdown_tables:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Compact Markdown Tables
          description: Remove extra whitespace padding in markdown table cells for more compact output
        output_tables_as_markdown:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Output Tables As Markdown
          description: Output tables as markdown pipe tables instead of HTML <table> tags. Markdown tables are simpler but cannot represent complex structures like merged cells
        markdown_table_multiline_separator:
          anyOf:
          - type: string
          - type: 'null'
          title: Markdown Table Multiline Separator
          description: 'Separator string for multiline cell content in markdown tables. Example: ''<br>'' to preserve line breaks, '' '' to join with spaces'
        merge_continued_tables:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Merge Continued Tables
          description: Automatically merge tables that span multiple pages into a single table. The merged table appears on the first page with merged_from_pages metadata
      additionalProperties: false
      type: object
      title: LlamaParseTables
      description: Table formatting options for markdown output.
    LlamaParsePresentationOptions:
      properties:
        out_of_bounds_content:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Out Of Bounds Content
          description: Extract content positioned outside the visible slide area. Some presentations have hidden notes or content that extends beyond slide boundaries
        skip_embedded_data:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Skip Embedded Data
          description: Skip extraction of embedded chart data tables. When true, only the visual representation of charts is captured, not the underlying data
      additionalProperties: false
      type: object
      title: LlamaParsePresentationOptions
      description: Presentation (PowerPoint, Keynote, ODP) parsing options.
    LlamaParseJobFailureConditions:
      properties:
        allowed_page_failure_ratio:
          anyOf:
          - type: number
            maximum: 1.0
            exclusiveMinimum: 0.0
          - type: 'null'
          title: Allowed Page Failure Ratio
          description: 'Maximum ratio of pages allowed to fail before the job fails (0-1). Example: 0.1 means job fails if more than 10% of pages fail. Default is 0.05 (5%)'
        fail_on_image_extraction_error:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Fail On Image Extraction Error
          description: Fail the entire job if any embedded image cannot be extracted. By default, image extraction errors are logged but don't fail the job
        fail_on_image_ocr_error:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Fail On Image Ocr Error
          description: Fail the entire job if OCR fails on any image. By default, OCR errors result in empty text for that image
        fail_on_markdown_reconstruction_error:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Fail On Markdown Reconstruction Error
          description: Fail the entire job if markdown cannot be reconstructed for any page. By default, failed pages use fallback text extraction
        fail_on_buggy_font:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Fail On Buggy Font
          description: Fail the job if a problematic font is detected that may cause incorrect text extraction. Buggy fonts can produce garbled or missing characters
      additionalProperties: false
      type: object
      title: LlamaParseJobFailureConditions
      description: 'Conditions that determine when a parsing job should fail vs complete with partial results.


        By default, jobs complete successfully even if some pages fail to parse.

        Use these settings to enforce stricter quality requirements.'
    ConfigurationResponse:
      properties:
        id:
          type: string
          title: Id
          description: Unique configuration ID.
        created_at:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Created At
          description: Creation timestamp.
        updated_at:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Updated At
          description: Last update timestamp.
        name:
          type: string
          title: Name
          description: Configuration name.
        product_type:
          type: string
          enum:
          - split_v1
          - extract_v2
          - classify_v2
          - parse_v2
          - spreadsheet_v1
          - unknown
          title: Product Type
          description: Product type.
        version:
          type: string
          title: Version
          description: Version identifier (datetime string).
        parameters:
          oneOf:
          - $ref: '#/components/schemas/SplitV1Parameters'
          - $ref: '#/components/schemas/ExtractV2Parameters'
          - $ref: '#/components/schemas/ClassifyV2Parameters'
          - $ref: '#/components/schemas/ParseV2Parameters'
          - $ref: '#/components/schemas/SpreadsheetV1Parameters'
          - $ref: '#/components/schemas/UntypedParameters'
          title: Parameters
          description: Product-specific configuration parameters.
          discriminator:
            propertyName: product_type
            mapping:
              classify_v2: '#/components/schemas/ClassifyV2Parameters'
              extract_v2: '#/components/schemas/ExtractV2Parameters'
              parse_v2: '#/components/schemas/ParseV2Parameters'
              split_v1: '#/components/schemas/SplitV1Parameters'
              spreadsheet_v1: '#/components/schemas/SpreadsheetV1Parameters'
              unknown: '#/components/schemas/UntypedParameters'
      type: object
      required:
      - id
      - name
      - product_type
      - version
      - parameters
      title: ConfigurationResponse
      description: Response schema for a single product configuration.
    LlamaParseOcrParameters:
      properties:
        languages:
          anyOf:
          - items:
              $ref: '#/components/schemas/ParserLanguages'
            type: array
          - type: 'null'
          title: Languages
          description: 'Languages to use for OCR text recognition. Specify multiple languages if document contains mixed-language content. Order matters - put primary language first. Example: [''en'', ''es''] for English with Spanish'
      additionalProperties: false
      type: object
      title: LlamaParseOcrParameters
      description: OCR (Optical Character Recognition) configuration parameters.
    AutoModeIgnoreOptions:
      properties:
        ignore_diagonal_text:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Ignore Diagonal Text
          description: Whether to ignore diagonal text in the document
        ignore_hidden_text:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Ignore Hidden Text
          description: Whether to ignore hidden text in the document
      additionalProperties: false
      type: object
      title: AutoModeIgnoreOptions
      description: Ignore options for auto mode parsing configuration.
    AutoModePresentationOptions:
      properties:
        out_of_bounds_content:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Out Of Bounds Content
          description: Extract out of bounds content in presentation slides
        skip_embedded_data:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Skip Embedded Data
          description: Skip extraction of embedded data for charts in presentation slides
      additionalProperties: false
      type: object
      title: AutoModePresentationOptions
      description: Presentation-specific options for auto mode parsing configuration.
    AutoModeCropBox:
      properties:
        bottom:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: 0.0
          - type: 'null'
          title: Bottom
          description: Bottom boundary of crop box as ratio (0-1)
        left:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: 0.0
          - type: 'null'
          title: Left
          description: Left boundary of crop box as ratio (0-1)
        right:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: 0.0
          - type: 'null'
          title: Right
          description: Right boundary of crop box as ratio (0-1)
        top:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: 0.0
          - type: 'null'
          title: Top
          description: Top boundary of crop box as ratio (0-1)
      additionalProperties: false
      type: object
      title: AutoModeCropBox
      description: Crop box options for auto mode parsing configuration.
    LlamaParseTablesAsSpreadsheetOptions:
      properties:
        enable:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Enable
          description: Whether this option is enabled
        guess_sheet_name:
          type: boolean
          title: Guess Sheet Name
          description: Automatically generate descriptive sheet names from table context (headers, surrounding text) instead of using generic names like 'Table_1'
          default: true
      additionalProperties: false
      type: object
      title: LlamaParseTablesAsSpreadsheetOptions
      description: Options for exporting extracted tables as XLSX spreadsheet files.
    ClassifyV2Parameters:
      properties:
        rules:
          items:
            $ref: '#/components/schemas/ClassifyV2Rule'
          type: array
          minItems: 1
          title: Rules
          description: Classify rules to evaluate against the document (at least one required)
        mode:
          type: string
          const: FAST
          title: Mode
          description: Classify execution mode
          default: FAST
        parsing_configuration:
          anyOf:
          - $ref: '#/components/schemas/ClassifyV2ParsingConfiguration'
          - type: 'null'
          description: Parsing configuration for controlling which pages are read
        product_type:
          type: string
          const: classify_v2
          title: Product Type
          description: Product type.
      type: object
      required:
      - rules
      - product_type
      title: ClassifyV2Parameters
      description: Typed parameters for a *classify v2* product configuration.
    AutoModeParsingConf:
      properties:
        tier:
          anyOf:
          - type: string
            enum:
            - fast
            - cost_effective
            - agentic
            - agentic_plus
          - type: 'null'
          title: Tier
          description: Override the parsing tier for matched pages. Must be paired with version
        version:
          anyOf:
          - type: string
            enum:
            - latest
            - '2026-06-05'
            - '2026-06-04'
            - '2025-12-11'
            x-enum-order-preserved: true
          - type: string
          - type: 'null'
          title: Version
          description: 'Version for the override tier. Required when `tier` is set. Use `latest`, or pin one of that tier''s dated versions.


            Current `latest` by tier:

            - `fast`: `2025-12-11`

            - `cost_effective`: `2026-06-05`

            - `agentic`: `2026-06-04`

            - `agentic_plus`: `2026-06-04`


            Full list: `GET /api/v2/parse/versions`.'
        custom_prompt:
          anyOf:
          - type: string
          - type: 'null'
          title: Custom Prompt
          description: Custom AI instructions for matched pages. Overrides the base custom_prompt
        ignore:
          anyOf:
          - $ref: '#/components/schemas/AutoModeIgnoreOptions'
          - type: 'null'
          description: Options for ignoring specific text types
        aggressive_table_extraction:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Aggressive Table Extraction
          description: Whether to use aggressive table extraction
        outlined_table_extraction:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Outlined Table Extraction
          description: Whether to use outlined table extraction
        adaptive_long_table:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Adaptive Long Table
          description: Whether to use adaptive long table handling
        extract_layout:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Extract Layout
          description: Whether to extract layout information
        specialized_chart_parsing:
          anyOf:
          - type: string
            enum:
            - agentic_plus
            - agentic
            - efficient
          - type: 'null'
          title: Specialized Chart Parsing
          description: Enable specialized chart parsing with the specified mode
        high_res_ocr:
          anyOf:
          - type: boolean
          - type: 'null'
          title: High Res Ocr
          description: Whether to use high resolution OCR
        language:
          anyOf:
          - type: string
          - type: 'null'
          title: Language
          description: Primary language of the document
        crop_box:
          anyOf:
          - $ref: '#/components/schemas/AutoModeCropBox'
          - type: 'null'
          description: Document crop box boundaries
        spatial_text:
          anyOf:
          - $ref: '#/components/schemas/AutoModeSpatialTextOptions'
          - type: 'null'
          description: Spatial text output options
        presentation:
          anyOf:
          - $ref: '#/components/schemas/AutoModePresentationOptions'
          - type: 'null'
          description: Presentation-specific parsing options
      additionalProperties: false
      type: object
      title: AutoModeParsingConf
      description: 'Parsing configuration applied when auto mode triggers match.


        These settings override the base configuration for pages where trigger conditions

        are satisfied. Only specify fields you want to override - unset fields inherit

        from the base configuration.'
    LlamaParseIgnoreOptions:
      properties:
        ignore_diagonal_text:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Ignore Diagonal Text
          description: Skip text rotated at an angle (not horizontal/vertical). Useful for ignoring watermarks or decorative angled text
        ignore_text_in_image:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Ignore Text In Image
          description: Skip OCR text extraction from embedded images. Use when images contain irrelevant text (watermarks, logos) that shouldn't be in the output
        ignore_hidden_text:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Ignore Hidden Text
          description: Skip text marked as hidden in the document structure. Some PDFs contain invisible text layers used for accessibility or search indexing
      additionalProperties: false
      type: object
      title: LlamaParseIgnoreOptions
      description: Options for ignoring specific types of text during extraction.
    AutoModeConfigurationEntry:
      properties:
        parsing_conf:
          $ref: '#/components/schemas/AutoModeParsingConf'
          description: Parsing configuration to apply when trigger conditions are met
        trigger_mode:
          anyOf:
          - type: string
          - type: 'null'
          title: Trigger Mode
          description: 'How to combine multiple trigger conditions: ''and'' (all conditions must match, this is the default) or ''or'' (any single condition can trigger)'
        page_md_error:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Page Md Error
          description: Trigger on pages with markdown extraction errors
        text_in_page:
          anyOf:
          - type: string
          - type: 'null'
          title: Text In Page
          description: Trigger if page text/markdown contains this string
        table_in_page:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Table In Page
          description: Trigger if page contains a table
        image_in_page:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Image In Page
          description: Trigger if page contains non-screenshot images
        full_page_image_in_page:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Full Page Image In Page
          description: Trigger if page contains a full-page image (scanned page detection)
        full_page_image_in_page_threshold:
          anyOf:
          - type: number
          - type: string
          - type: 'null'
          title: Full Page Image In Page Threshold
          description: Threshold for full page image detection (0.0-1.0, default 0.8)
        filename_regexp:
          anyOf:
          - type: string
          - type: 'null'
          title: Filename Regexp
          description: Regex pattern to match against filename
        filename_regexp_mode:
          anyOf:
          - type: string
          - type: 'null'
          title: Filename Regexp Mode
          description: Regex mode flags (e.g., 'i' for case-insensitive)
        filename_match_glob:
          anyOf:
          - type: string
          - type: 'null'
          title: Filename Match Glob
          description: Single glob pattern to match against filename
        filename_match_glob_list:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Filename Match Glob List
          description: List of glob patterns to match against filename
        page_longer_than_n_chars:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Longer Than N Chars
          description: Trigger if page has more than N characters
        page_shorter_than_n_chars:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Shorter Than N Chars
          description: Trigger if page has fewer than N characters
        page_contains_at_least_n_words:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Least N Words
          description: Trigger if page has more than N words
        page_contains_at_most_n_words:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Most N Words
          description: Trigger if page has fewer than N words
        page_contains_at_least_n_lines:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Least N Lines
          description: Trigger if page has more than N lines
        page_contains_at_most_n_lines:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Most N Lines
          description: Trigger if page has fewer than N lines
        page_contains_at_least_n_images:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Least N Images
          description: Trigger if page has more than N images
        page_contains_at_most_n_images:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Most N Images
          description: Trigger if page has fewer than N images
        page_contains_at_least_n_tables:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Least N Tables
          description: Trigger if page has more than N tables
        page_contains_at_most_n_tables:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Most N Tables
          description: Trigger if page has fewer than N tables
        page_contains_at_least_n_links:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Least N Links
          description: Trigger if page has more than N links
        page_contains_at_most_n_links:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Most N Links
          description: Trigger if page has fewer than N links
        page_contains_at_least_n_charts:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Least N Charts
          description: Trigger if page has more than N charts
        page_contains_at_most_n_charts:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Most N Charts
          description: Trigger if page has fewer than N charts
        page_contains_at_least_n_layout_elements:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Least N Layout Elements
          description: Trigger if page has more than N layout elements
        page_contains_at_most_n_layout_elements:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Most N Layout Elements
          description: Trigger if page has fewer than N layout elements
        page_contains_at_least_n_percent_numbers:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Least N Percent Numbers
          description: Trigger if page has more than N% numeric words
        page_contains_at_most_n_percent_numbers:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Most N Percent Numbers
          description: Trigger if page has fewer than N% numeric words
        page_contains_at_least_n_numbers:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Least N Numbers
          description: Trigger if page has more than N numeric words
        page_contains_at_most_n_numbers:
          anyOf:
          - type: integer
          - type: string
          - type: 'null'
          title: Page Contains At Most N Numbers
          description: Trigger if page has fewer than N numeric words
        regexp_in_page:
          anyOf:
          - type: string
          - type: 'null'
          title: Regexp In Page
          description: Regex pattern to match in page content
        regexp_in_page_mode:
          anyOf:
          - type: string
          - type: 'null'
          title: Regexp In Page Mode
          description: Regex mode flags for regexp_in_page
        layout_element_in_page:
          anyOf:
          - type: string
          - type: 'null'
          title: Layout Element In Page
          description: Trigger if page contains this layout element type
        layout_element_in_page_confidence_threshold:
          anyOf:
          - type: number
          - type: string
          - type: 'null'
          title: Layout Element In Page Confidence Threshold
          description: Confidence threshold for layout element detection
      additionalProperties: false
      type: object
      required:
      - parsing_conf
      title: AutoModeConfigurationEntry
      description: 'A single auto mode rule with trigger conditions and parsing configuration.


        Auto mode allows conditional parsing where different configurations are applied

        based on page content, structure, or filename. When triggers match, the

        parsing_conf overrides default settings for that page.'
      examples:
      - parsing_conf:
          tier: agentic
          version: latest
        table_in_page: true
      - image_in_page: true
        parsing_conf:
          tier: agentic
          version: latest
      - filename_match_glob: '*.txt'
        parsing_conf:
          tier: fast
          version: latest
    ConfigurationCreateRequest:
      properties:
        name:
          type: string
          maxLength: 255
          minLength: 1
          title: Name
          description: Human-readable name for this configuration.
        parameters:
          oneOf:
          - $ref: '#/components/schemas/SplitV1Parameters'
          - $ref: '#/components/schemas/ExtractV2Parameters'
          - $ref: '#/components/schemas/ClassifyV2Parameters'
          - $ref: '#/components/schemas/ParseV2Parameters'
          - $ref: '#/components/schemas/SpreadsheetV1Parameters'
          - $ref: '#/components/schemas/UntypedParameters'
          title: Parameters
          description: Product-specific configuration parameters.
          discriminator:
            propertyName: product_type
            mapping:
              classify_v2: '#/components/schemas/ClassifyV2Parameters'
              extract_v2: '#/components/schemas/ExtractV2Parameters'
              parse_v2: '#/components/schemas/ParseV2Parameters'
              split_v1: '#/components/schemas/SplitV1Parameters'
              spreadsheet_v1: '#/components/schemas/SpreadsheetV1Parameters'
              unknown: '#/components/schemas/UntypedParameters'
      type: object
      required:
      - name
      - parameters
      title: ConfigurationCreateRequest
      description: Request body for creating a product configuration.
    LlamaParseOutputOptions:
      properties:
        markdown:
          $ref: '#/components/schemas/LlamaParseMarkdownOptions'
          description: Markdown formatting options including table styles and link annotations
        spatial_text:
          $ref: '#/components/schemas/LlamaParseSpatialTextOptions'
          description: Spatial text output options for preserving document layout structure
        tables_as_spreadsheet:
          $ref: '#/components/schemas/LlamaParseTablesAsSpreadsheetOptions'
          description: Options for exporting tables as XLSX spreadsheets
        extract_printed_page_number:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Extract Printed Page Number
          description: Extract the printed page number as it appears in the document (e.g., 'Page 5 of 10', 'v', 'A-3'). Useful for referencing original page numbers
        images_to_save:
          items:
            type: string
            enum:
            - screenshot
            - embedded
            - layout
          type: array
          title: Images To Save
          description: 'Image categories to extract and save. Options: ''screenshot'' (full page renders useful for visual QA), ''embedded'' (images found within the document), ''layout'' (cropped regions from layout detection like figures and diagrams). Empty list saves no images'
        additional_outputs:
          items:
            type: string
          type: array
          title: Additional Outputs
          description: 'Optional additional output artifacts to save alongside the primary parse output. Each value opts in to generating and persisting one extra file; the empty list (default) saves none. The three accepted values are: ''stripped_md'' — per-page markdown stripped of formatting (links, bold/italic, images, HTML), saved as JSON for full-text-search indexing; fetch via `expand=stripped_markdown_content_metadata`. ''concatenated_stripped_txt'' — all stripped pages concatenated into a single plain-text file with `\n\n---\n\n` between pages, useful for feeding the document into search or embedding pipelines as one blob; fetch via `expand=concatenated_stripped_markdown_content_metadata`. ''word_bbox'' — raw word-level bounding boxes (one JSON object per word, with page number and x/y/w/h coordinates) saved as JSONL, useful for highlighting or grounding extracted answers back to the source document; fetch via `expand=raw_words_content_metadata`.'
          examples:
          - - stripped_md
            - concatenated_stripped_txt
            - word_bbox
        granular_bboxes:
          items:
            type: string
            enum:
            - cell
            - line
            - word
          type: array
          title: Granular Bboxes
          description: Bounding-box granularity levels to compute for the parse. 'word' computes one bounding box per detected word; 'line' computes one per text line; 'cell' computes one per table cell. Multiple levels can be requested. Empty list (default) disables granular bboxes — only item-level layout boxes are returned on the result. When set, the computed boxes are not inlined on the result items; they are written to a separate `grounded_items` sidecar (JSONL, one row per page) and exposed as `result_content_metadata.grounded_items` (a presigned download URL) on the parse result. Each row matches the `GroundedJsonItem` shape.
          examples:
          - - word
            - line
            - cell
      additionalProperties: false
      type: object
      title: LlamaParseOutputOptions
      description: 'Output formatting and content extraction options.


        Controls how parsed content is formatted and what additional data is extracted.'
    LlamaParseMarkdownOptions:
      properties:
        annotate_links:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Annotate Links
          description: Add link annotations to markdown output in the format [text](url). When false, only the link text is included
        tables:
          $ref: '#/components/schemas/LlamaParseTables'
          description: Table formatting options including markdown vs HTML format and merging behavior
        inline_images:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Inline Images
          description: Embed images directly in markdown as base64 data URIs instead of extracting them as separate files. Useful for self-contained markdown output
      additionalProperties: false
      type: object
      title: LlamaParseMarkdownOptions
      description: Markdown output formatting options.
    LlamaParseAgenticOptions:
      properties:
        custom_prompt:
          anyOf:
          - type: string
          - type: 'null'
          title: Custom Prompt
          description: 'Custom instructions for the AI parser. Use to guide extraction behavior, specify output formatting, or provide domain-specific context. Example: ''Extract financial tables with currency symbols. Format dates as YYYY-MM-DD.'''
      additionalProperties: false
      type: object
      title: LlamaParseAgenticOptions
      description: 'Options for AI-powered parsing tiers (cost_effective, agentic, agentic_plus).


        These options customize how the AI processes and interprets document content.

        Only applicable when using non-fast tiers.'
    SplitCategory:
      properties:
        name:
          type: string
          maxLength: 200
          minLength: 1
          title: Name
          description: Name of the category.
        description:
          anyOf:
          - type: string
            maxLength: 2000
            minLength: 1
          - type: 'null'
          title: Description
          description: Optional description of what content belongs in this category.
      type: object
      required:
      - name
      title: SplitCategory
      description: Category definition for document splitting.
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    ConfigurationUpdateRequest:
      properties:
        name:
          anyOf:
          - type: string
            maxLength: 255
            minLength: 1
          - type: 'null'
          title: Name
          description: Updated name (omit to leave unchanged).
        parameters:
          anyOf:
          - oneOf:
            - $ref: '#/components/schemas/SplitV1Parameters'
            - $ref: '#/components/schemas/ExtractV2Parameters'
            - $ref: '#/components/schemas/ClassifyV2Parameters'
            - $ref: '#/components/schemas/ParseV2Parameters'
            - $ref: '#/components/schemas/SpreadsheetV1Parameters'
            - $ref: '#/components/schemas/UntypedParameters'
            discriminator:
              propertyName: product_type
              mapping:
                classify_v2: '#/components/schemas/ClassifyV2Parameters'
                extract_v2: '#/components/schemas/ExtractV2Parameters'
                parse_v2: '#/components/schemas/ParseV2Parameters'
                split_v1: '#/components/schemas/SplitV1Parameters'
                spreadsheet_v1: '#/components/schemas/SpreadsheetV1Parameters'
                unknown: '#/components/schemas/UntypedParameters'
          - type: 'null'
          title: Parameters
          description: Updated parameters (omit to leave unchanged).
      type: object
      title: ConfigurationUpdateRequest
      description: Request body for updating a product configuration.
    ParseV2Parameters:
      properties:
        tier:
          type: string
          enum:
          - fast
          - cost_effective
          - agentic
          - agentic_plus
          title: Tier
          description: 'Parsing tier: ''fast'' (rule-based, cheapest), ''cost_effective'' (balanced), ''agentic'' (AI-powered with custom prompts), or ''agentic_plus'' (premium AI with highest accuracy)'
        version:
          anyOf:
          - type: string
            enum:
            - latest
            - '2026-06-05'
            - '2026-06-04'
            - '2025-12-11'
            x-enum-order-preserved: true
          - type: string
          title: Version
          description: 'Version for the selected tier. Use `latest`, or pin one of that tier''s dated versions.


            Current `latest` by tier:

            - `fast`: `2025-12-11`

            - `cost_effective`: `2026-06-05`

            - `agentic`: `2026-06-04`

            - `agentic_plus`: `2026-06-04`


            Full list: `GET /api/v2/parse/versions`.'
        client_name:
          anyOf:
          - type: string
          - type: 'null'
          title: Client Name
          description: 'Identifier for the client/application making the request. Used for analytics and debugging. Example: ''my-app-v2'''
        processing_options:
          $ref: '#/components/schemas/LlamaParseProcessingOptions'
          description: Document processing options including OCR, table extraction, and chart parsing
        fast_options:
          anyOf:
          - $ref: '#/components/schemas/LlamaParseFastOptions'
          - type: 'null'
          description: Fast tier configuration options. Auto-initialized when tier='fast'. Cannot be used with other tiers
        agentic_options:
          anyOf:
          - $ref: '#/components/schemas/LlamaParseAgenticOptions'
          - type: 'null'
          description: AI-powered tier configuration (custom prompts). Auto-initialized for cost_effective/agentic/agentic_plus tiers. Cannot be used with fast tier
        webhook_configurations:
          items:
            $ref: '#/components/schemas/LlamaParseWebhookConfiguration'
          type: array
          title: Webhook Configurations
          description: Webhook endpoints for job status notifications. Multiple webhooks can be configured for different events or services
        input_options:
          $ref: '#/components/schemas/LlamaParseInputOptions'
          description: Format-specific options (HTML, PDF, spreadsheet, presentation). Applied based on detected input file type
        crop_box:
          $ref: '#/components/schemas/LlamaParseCropBox'
          description: Crop boundaries to process only a portion of each page. Values are ratios 0-1 from page edges
        page_ranges:
          $ref: '#/components/schemas/LlamaParsePageRanges'
          description: 'Page selection: limit total pages or specify exact pages to process'
        disable_cache:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Disable Cache
          description: Bypass result caching and force re-parsing. Use when document content may have changed or you need fresh results
        output_options:
          $ref: '#/components/schemas/LlamaParseOutputOptions'
          description: Output formatting options for markdown, text, and extracted images
        processing_control:
          $ref: '#/components/schemas/LlamaParseProcessingControl'
          description: Job execution controls including timeouts and failure thresholds
        product_type:
          type: string
          const: parse_v2
          title: Product Type
          description: Product type.
      type: object
      required:
      - tier
      - version
      - product_type
      title: ParseV2Parameters
      description: 'Configuration for LlamaParse v2 document parsing.


        Includes tier selection, processing options, output formatting,

        page targeting, and webhook delivery. Refer to the LlamaParse

        documentation for details on each field.'
    LlamaParseHtmlOptions:
      properties:
        make_all_elements_visible:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Make All Elements Visible
          description: Force all HTML elements to be visible by overriding CSS display/visibility properties. Useful for parsing pages with hidden content or collapsed sections
        remove_fixed_elements:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Remove Fixed Elements
          description: Remove fixed-position elements (headers, footers, floating buttons) that appear on every page render
        remove_navigation_elements:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Remove Navigation Elements
          description: Remove navigation elements (nav bars, sidebars, menus) to focus on main content
      additionalProperties: false
      type: object
      title: LlamaParseHtmlOptions
      description: HTML/web page parsing options.
    LlamaParseWebhookConfiguration:
      properties:
        webhook_url:
          anyOf:
          - type: string
            pattern: '^https?:'
          - type: 'null'
          title: Webhook Url
          description: HTTPS URL to receive webhook POST requests. Must be publicly accessible
        webhook_headers:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Webhook Headers
          description: 'Custom HTTP headers to include in webhook requests. Use for authentication tokens or custom routing. Example: {''Authorization'': ''Bearer xyz''}'
        webhook_events:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Webhook Events
          description: 'Events that trigger this webhook. Options: ''parse.success'' (job completed), ''parse.error'' (job failed), ''parse.partial_success'' (some pages failed), ''parse.pending'', ''parse.running'', ''parse.cancelled''. If not specified, webhook fires for all events'
          examples:
          - - parse.success
            - parse.error
        webhook_output_format:
          anyOf:
          - type: string
            enum:
            - string
            - json
          - type: 'null'
          title: Webhook Output Format
          description: Format of the webhook payload body. 'string' (default) sends the payload as a JSON-encoded string; 'json' sends it as a JSON object.
          examples:
          - json
      additionalProperties: false
      type: object
      title: LlamaParseWebhookConfiguration
      description: 'Webhook configuration for receiving parsing job notifications.


        Webhooks are called when specified events occur during job processing.

        Configure multiple webhook configurations to send to different endpoints.'
    ConfigurationQueryResponse:
      properties:
        items:
          items:
            $ref: '#/components/schemas/ConfigurationResponse'
          type: array
          title: Items
          description: The list of items.
        next_page_token:
          anyOf:
          - type: string
          - type: 'null'
          title: Next Page Token
          description: 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:
          anyOf:
          - type: integer
          - type: 'null'
          title: Total Size
          description: 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.
      type: object
      required:
      - items
      title: ConfigurationQueryResponse
      description: Paginated list of product configurations.
    LlamaParseCropBox:
      properties:
        bottom:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: 0.0
          - type: 'null'
          title: Bottom
          description: Bottom boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content below this line is excluded
        left:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: 0.0
          - type: 'null'
          title: Left
          description: Left boundary as ratio (0-1). 0=left edge, 1=right edge. Content left of this line is excluded
        right:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: 0.0
          - type: 'null'
          title: Right
          description: Right boundary as ratio (0-1). 0=left edge, 1=right edge. Content right of this line is excluded
        top:
          anyOf:
          - type: number
            maximum: 1.0
            minimum: 0.0
          - type: 'null'
          title: Top
          description: Top boundary as ratio (0-1). 0=top edge, 1=bottom edge. Content above this line is excluded
      additionalProperties: false
      type: object
      title: LlamaParseCropBox
      description: 'Crop box boundaries for processing only a portion of each page.


        All values are ratios from 0 to 1, where (0,0) is the top-left corner and (1,1) is

        the bottom-right corner. For example, to process only the top half of each page,

        set bottom=0.5 (keeping top=0, left=0, right=1).'
    ClassifyV2ParsingConfiguration:
      properties:
        lang:
          type: string
          title: Lang
          description: ISO 639-1 language code for the document
          default: en
          examples:
          - en
          - es
          - zh
        target_pages:
          anyOf:
          - type: string
          - type: 'null'
          title: Target Pages
          description: Comma-separated page numbers or ranges to process (1-based). Omit to process all pages.
          examples:
          - 1,3,5-7
          - 1-3,8-10
        max_pages:
          anyOf:
          - type: integer
            minimum: 1.0
          - type: 'null'
          title: Max Pages
          description: Maximum number of pages to process. Omit for no limit.
          examples:
          - 10
      type: object
      title: ClassifyV2ParsingConfiguration
      description: Parsing configuration for classify jobs.
    ParserLanguages:
      type: string
      enum:
      - af
      - az
      - bs
      - cs
      - cy
      - da
      - de
      - en
      - es
      - et
      - fr
      - ga
      - hr
      - hu
      - id
      - is
      - it
      - ku
      - la
      - lt
      - lv
      - mi
      - ms
      - mt
      - nl
      - 'no'
      - oc
      - pi
      - pl
      - pt
      - ro
      - rs_latin
      - sk
      - sl
      - sq
      - sv
      - sw
      - tl
      - tr
      - uz
      - vi
      - ar
      - fa
      - ug
      - ur
      - bn
      - as
      - mni
      - ru
      - rs_cyrillic
      - be
      - bg
      - uk
      - mn
      - abq
      - ady
      - kbd
      - ava
      - dar
      - inh
      - che
      - lbe
      - lez
      - tab
      - tjk
      - hi
      - mr
      - ne
      - bh
      - mai
      - ang
      - bho
      - mah
      - sck
      - new
      - gom
      - sa
      - bgc
      - th
      - ch_sim
      - ch_tra
      - ja
      - ko
      - ta
      - te
      - kn
      title: ParserLanguages
      description: Enum for representing the languages supported by the parser.
    LlamaParseProcessingOptions:
      properties:
        ignore:
          $ref: '#/components/schemas/LlamaParseIgnoreOptions'
          description: Options for ignoring specific text types (diagonal, hidden, text in images)
        ocr_parameters:
          $ref: '#/components/schemas/LlamaParseOcrParameters'
          description: OCR configuration including language detection settings
        aggressive_table_extraction:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Aggressive Table Extraction
          description: Use aggressive heuristics to detect table boundaries, even without visible borders. Useful for documents with borderless or complex tables
        disable_heuristics:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Disable Heuristics
          description: Disable automatic heuristics including outlined table extraction and adaptive long table handling. Use when heuristics produce incorrect results
        specialized_chart_parsing:
          anyOf:
          - type: string
            enum:
            - agentic_plus
            - agentic
            - efficient
          - type: 'null'
          title: Specialized Chart Parsing
          description: 'Enable AI-powered chart analysis. Modes: ''efficient'' (fast, lower cost), ''agentic'' (balanced), ''agentic_plus'' (highest accuracy). Automatically enables extract_layout and precise_bounding_box when set'
        cost_optimizer:
          anyOf:
          - $ref: '#/components/schemas/LlamaParseCostOptimizerParameters'
          - type: 'null'
          description: Cost optimization settings. Only available with 'agentic' or 'agentic_plus' tiers
        auto_mode_configuration:
          anyOf:
          - items:
              $ref: '#/components/schemas/AutoModeConfigurationEntry'
            type: array
          - type: 'null'
          title: Auto Mode Configuration
          description: Conditional processing rules that apply different parsing options based on page content, document structure, or filename patterns. Each entry defines trigger conditions and the parsing configuration to apply when triggered
      additionalProperties: false
      type: object
      title: LlamaParseProcessingOptions
      description: 'Processing options shared across all parsing tiers.


        These options control how documents are analyzed and processed regardless of the selected tier.

        Some options automatically enable additional behaviors (e.g., specialized_chart_parsing

        enables extract_layout and precise_bounding_box).'
    LlamaParseCostOptimizerParameters:
      properties:
        enable:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Enable
          description: 'Enable cost-optimized parsing. Routes simpler pages to faster processing while complex pages use full AI analysis. May reduce speed on some documents. IMPORTANT: Only available with ''agentic'' or ''agentic_plus'' tiers'
      additionalProperties: false
      type: object
      title: LlamaParseCostOptimizerParameters
      description: 'Cost optimizer configuration for reducing parsing costs on simpler pages.


        When enabled, the parser analyzes each page and routes simpler pages to faster,

        cheaper processing while preserving quality for complex pages. Only works with

        ''agentic'' or ''agentic_plus'' tiers.'
    LlamaParseSpreadsheetOptions:
      properties:
        detect_sub_tables_in_sheets:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Detect Sub Tables In Sheets
          description: Detect and extract multiple tables within a single sheet. Useful when spreadsheets contain several data regions separated by blank rows/columns
        force_formula_computation_in_sheets:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Force Formula Computation In Sheets
          description: Compute formula results instead of extracting formula text. Use when you need calculated values rather than formula definitions
        include_hidden_sheets:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Include Hidden Sheets
          description: Parse hidden sheets in addition to visible ones. By default, hidden sheets are skipped
      additionalProperties: false
      type: object
      title: LlamaParseSpreadsheetOptions
      description: Spreadsheet (Excel, CSV, ODS) parsing options.
    AutoModeSpatialTextOptions:
      properties:
        preserve_layout_alignment_across_pages:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Preserve Layout Alignment Across Pages
          description: Preserve text alignment across page boundaries
        preserve_very_small_text:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Preserve Very Small Text
          description: Include very small text in spatial output
        do_not_unroll_columns:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Do Not Unroll Columns
          description: Keep column structure intact without unrolling
      additionalProperties: false
      type: object
      title: AutoModeSpatialTextOptions
      description: Spatial text options for auto mode parsing configuration.
    SpreadsheetV1Parameters:
      properties:
        sheet_names:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Sheet Names
          description: The names of the sheets to extract regions from. If empty, all sheets will be processed.
        include_hidden_cells:
          type: boolean
          title: Include Hidden Cells
          description: Whether to include hidden cells when extracting regions from the spreadsheet.
          default: true
        extraction_range:
          anyOf:
          - type: string
          - type: 'null'
          title: Extraction Range
          description: A1 notation of the range to extract a single region from. If None, the entire sheet is used.
        generate_additional_metadata:
          type: boolean
          title: Generate Additional Metadata
          description: Whether to generate additional metadata (title, description) for each extracted region.
          default: true
        use_experimental_processing:
          type: boolean
          title: Use Experimental Processing
          description: Enables experimental processing. Accuracy may be impacted.
          default: false
        flatten_hierarchical_tables:
          type: boolean
          title: Flatten Hierarchical Tables
          description: Return a flattened dataframe when a detected table is recognized as hierarchical.
          default: false
        table_merge_sensitivity:
          type: string
          enum:
          - strong
          - weak
          title: Table Merge Sensitivity
          description: Influences how likely similar-looking regions are merged into a single table. Useful for spreadsheets that either have sparse tables (strong merging) or many distinct tables close together (weak merging).
          default: strong
        specialization:
          anyOf:
          - type: string
          - type: 'null'
          title: Specialization
          description: 'Optional specialization mode for domain-specific extraction. Supported values: ''financial-standard'', ''financial-enhanced'', ''financial-precise''. Default None uses the general-purpose pipeline.'
        product_type:
          type: string
          const: spreadsheet_v1
          title: Product Type
          description: Product type.
      type: object
      required:
      - product_type
      title: SpreadsheetV1Parameters
      description: Typed parameters for a *spreadsheet v1* product configuration.
    LlamaParsePageRanges:
      properties:
        max_pages:
          anyOf:
          - type: integer
            minimum: 1.0
          - type: 'null'
          title: Max Pages
          description: Maximum number of pages to process. Pages are processed in order starting from page 1. If both max_pages and target_pages are set, target_pages takes precedence
        target_pages:
          anyOf:
          - type: string
          - type: 'null'
          title: Target Pages
          description: 'Comma-separated list of specific pages to process using 1-based indexing. Supports individual pages and ranges. Examples: ''1,3,5'' (pages 1, 3, 5), ''1-5'' (pages 1 through 5 inclusive), ''1,3,5-8,10'' (pages 1, 3, 5-8, and 10). Pages are sorted and deduplicated automatically. Duplicate pages cause an error'
      additionalProperties: false
      type: object
      title: LlamaParsePageRanges
      description: Page selection options for processing specific pages or limiting page count.
    LlamaParsePdfOptions:
      properties: {}
      additionalProperties: false
      type: object
      title: LlamaParsePdfOptions
    SplitStrategy:
      properties:
        allow_uncategorized:
          type: string
          enum:
          - include
          - forbid
          - omit
          title: Allow Uncategorized
          description: 'Controls handling of pages that don''t match any category. ''include'': pages can be grouped as ''uncategorized'' and included in results. ''forbid'': all pages must be assigned to a defined category. ''omit'': pages can be classified as ''uncategorized'' but are excluded from results.'
          default: include
      type: object
      title: SplitStrategy
      description: Configuration for how to split the document.
    LlamaParseTimeouts:
      properties:
        base_in_seconds:
          anyOf:
          - type: integer
            maximum: 7200.0
            exclusiveMinimum: 0.0
          - type: 'null'
          title: Base In Seconds
          description: Base timeout for the job in seconds (max 7200 = 2 hours). This is the minimum time allowed regardless of document size
        extra_time_per_page_in_seconds:
          anyOf:
          - type: integer
            maximum: 300.0
            exclusiveMinimum: 0.0
          - type: 'null'
          title: Extra Time Per Page In Seconds
          description: Additional timeout per page in seconds (max 300 = 5 minutes). Total timeout = base + (this value × page count)
      additionalProperties: false
      type: object
      title: LlamaParseTimeouts
      description: 'Job timeout configuration.


        Total timeout = base_in_seconds + (extra_time_per_page_in_seconds × page_count).

        Use these settings for large documents or complex parsing that needs more time.'
  securitySchemes:
    HTTPBearer:
      type: http
      scheme: bearer