marker_api/marker_endpoint_reference.md

2. Datalab Marker (PDF to Markdown) [1]

The Datalab Marker API is used for converting documents like PDFs into structured Markdown. Key endpoints include: [1, 2]

• POST /convert-document: High-level endpoint to convert files to Markdown.
• POST /extract-structured-data: Extracts specific fields from documents using JSON schemas.
• GET /convert-result-check: Polls for the status of a conversion task.
• POST /marker: (Now deprecated in favor of specific document conversion endpoints). [1, 2, 3]

A datalab marker-api client https://github.com/datalab-to/sdk.git

---

Documentation

Documentation Index

Fetch the complete documentation index at: https://documentation.datalab.to/llms.txt Use this file to discover all available pages before exploring further.

API Overview

REST API reference for document conversion, form filling, and file management.

Datalab provides REST APIs for document conversion, structured extraction, form filling, and file management. All APIs use the same authentication and follow similar patterns.

For the simplest integration, use the [Python SDK](/docs/welcome/sdk). The SDK handles authentication, polling, and provides typed responses.

Authentication

All requests require an API key in the X-API-Key header:

curl -X POST https://www.datalab.to/api/v1/convert \
  -H "X-API-Key: YOUR_API_KEY" \
  -F "file=@document.pdf"

Get your API key from the API Keys dashboard.

Request Pattern

All processing endpoints follow this pattern:

1. Submit a document for processing (returns immediately with a request_id)
2. Poll the status endpoint until processing completes
3. Retrieve results from the completed response

Submit Request

POST /api/v1/{endpoint}

Response:

{
  "success": true,
  "request_id": "abc123",
  "request_check_url": "https://www.datalab.to/api/v1/{endpoint}/abc123"
}

Poll for Results

GET /api/v1/{endpoint}/{request_id}

Response while processing:

{
  "status": "processing"
}

Response when complete:

{
  "status": "complete",
  "success": true,
  ...results...
}

Results are deleted from Datalab servers one hour after processing completes. Retrieve your results promptly.

Document Conversion

Convert documents to Markdown, HTML, JSON, or chunks.

Endpoint: POST /api/v1/convert

Request

import requests

url = "https://www.datalab.to/api/v1/convert"
headers = {"X-API-Key": "YOUR_API_KEY"}

with open("document.pdf", "rb") as f:
    response = requests.post(
        url,
        files={"file": ("document.pdf", f, "application/pdf")},
        data={
            "output_format": "markdown",
            "mode": "balanced",
        },
        headers=headers
    )

data = response.json()
check_url = data["request_check_url"]

Parameters

Parameter	Type	Default	Description
file	file	-	Document file (multipart upload)
file_url	string	-	URL to document (alternative to file upload)
output_format	string	markdown	Output format: markdown, html, json, chunks
mode	string	fast	Processing mode: fast, balanced, accurate
max_pages	int	-	Maximum pages to process
page_range	string	-	Specific pages (e.g., "0-5,10", 0-indexed). For spreadsheets, filters by sheet index.
paginate	bool	false	Add page delimiters to output
skip_cache	bool	false	Skip cached results
disable_image_extraction	bool	false	Don't extract images
disable_image_captions	bool	false	Don't generate image captions
save_checkpoint	bool	false	Save checkpoint for reuse
extras	string	-	Comma-separated: track_changes, chart_understanding, extract_links, table_row_bboxes, infographic, new_block_types
add_block_ids	bool	false	Add block IDs to HTML for citations
include_markdown_in_chunks	bool	false	Include markdown content in chunks output
token_efficient_markdown	bool	false	Optimize markdown for LLM token efficiency
fence_synthetic_captions	bool	false	Wrap synthetic image captions in HTML comments
additional_config	string	-	JSON with extra config options
webhook_url	string	-	Override webhook URL for this request

Processing Modes

Mode	Description
fast	Lowest latency, good for simple documents (default)
balanced	Balance of speed and accuracy
accurate	Highest accuracy, best for complex layouts

Response

Poll request_check_url until status is complete:

import time

while True:
    response = requests.get(check_url, headers=headers)
    result = response.json()

    if result["status"] == "complete":
        break
    time.sleep(2)

print(result["markdown"])

Response fields:

Field	Type	Description
status	string	processing, complete, or failed
success	bool	Whether conversion succeeded
markdown	string	Markdown output (if format is markdown)
html	string	HTML output (if format is html)
json	object	JSON output (if format is json)
chunks	object	Chunked output (if format is chunks)
images	object	Extracted images as {filename: base64}
metadata	object	Document metadata
page_count	int	Number of pages processed
parse_quality_score	float	Quality score (0-5)
cost_breakdown	object	Cost in cents
error	string	Error message if failed

For structured data extraction, see the [Extract endpoint](#structured-extraction). For document segmentation, see the [Segment endpoint](#document-segmentation).

Structured Extraction

Extract structured data from documents using a JSON schema.

Endpoint: POST /api/v1/extract

Request

import requests
import json

headers = {"X-API-Key": "YOUR_API_KEY"}

schema = {
    "invoice_number": {"type": "string", "description": "Invoice ID"},
    "total": {"type": "number", "description": "Total amount"},
    "line_items": {
        "type": "array",
        "items": {
            "type": "object",
            "properties": {
                "description": {"type": "string"},
                "amount": {"type": "number"}
            }
        }
    }
}

response = requests.post(
    "https://www.datalab.to/api/v1/extract",
    files={"file": ("invoice.pdf", open("invoice.pdf", "rb"), "application/pdf")},
    data={
        "page_schema": json.dumps(schema),
        "mode": "balanced"
    },
    headers=headers
)

data = response.json()
check_url = data["request_check_url"]

Parameters

Parameter	Type	Default	Description
file	file	-	Document file (multipart upload)
file_url	string	-	URL to document (alternative to file upload)
page_schema	string	-	JSON schema defining the data to extract. Required unless schema_id is provided.
schema_id	string	-	ID of a saved extraction schema (e.g. sch_k8Hx9mP2nQ4v). Mutually exclusive with page_schema.
schema_version	int	-	Version of the saved schema to use. Only valid with schema_id; defaults to the latest version.
checkpoint_id	string	-	Checkpoint ID from a previous /convert call (with save_checkpoint=true). Skips re-parsing.
mode	string	fast	Processing mode: fast, balanced, accurate
output_format	string	markdown	Output format: markdown, html, json, chunks
max_pages	int	-	Maximum pages to process
page_range	string	-	Specific pages (e.g., "0-5,10", 0-indexed). For spreadsheets, filters by sheet index.
save_checkpoint	bool	false	Save a checkpoint after processing for reuse with subsequent calls
webhook_url	string	-	Override webhook URL for this request

The extracted data is returned in extraction_schema_json in the poll response.

See Structured Extraction for detailed examples.

Document Segmentation

Segment documents into structured sections using a JSON schema.

Endpoint: POST /api/v1/segment

Parameters

Parameter	Type	Default	Description
file	file	-	Document file (multipart upload)
file_url	string	-	URL to document (alternative to file upload)
segmentation_schema	string	required	JSON schema defining the segments to extract
checkpoint_id	string	-	Checkpoint ID from a previous /convert call (with save_checkpoint=true). Skips re-parsing.
mode	string	fast	Processing mode: fast, balanced, accurate

See Document Segmentation for detailed examples.

Track Changes

Extract tracked changes (insertions and deletions) from DOCX files.

Endpoint: POST /api/v1/track-changes

response = requests.post(
    "https://www.datalab.to/api/v1/track-changes",
    files={"file": ("document.docx", open("document.docx", "rb"), "application/vnd.openxmlformats-officedocument.wordprocessingml.document")},
    headers=headers
)

See Track Changes for detailed examples.

Custom Processor

This feature is currently in beta. The API may change.

Execute custom AI-powered processors on documents.

Endpoint: POST /api/v1/custom-processor

`POST /api/v1/custom-pipeline` is deprecated (sunset: September 30, 2026). Migrate to `POST /api/v1/custom-processor`.

Parameters

Parameter	Type	Default	Description
file	file	-	Document file (multipart upload)
file_url	string	-	URL to document
pipeline_id	string	required	Custom processor ID (cp_XXXXX)
version	int	-	Processor version to run (default: active version)
run_eval	bool	false	Run evaluation rules defined for the processor
mode	string	fast	Processing mode: fast, balanced, accurate
output_format	string	markdown	Output format: markdown, html, json, chunks
webhook_url	string	-	URL to POST when complete

Form Filling

Fill forms in PDFs and images.

Endpoint: POST /api/v1/fill

Request

import json

field_data = {
    "full_name": {"value": "John Doe", "description": "Full legal name"},
    "date": {"value": "2024-01-15", "description": "Today's date"},
    "signature": {"value": "John Doe", "description": "Signature field"}
}

response = requests.post(
    "https://www.datalab.to/api/v1/fill",
    files={"file": ("form.pdf", open("form.pdf", "rb"), "application/pdf")},
    data={
        "field_data": json.dumps(field_data),
        "confidence_threshold": "0.5"
    },
    headers=headers
)

Parameters

Parameter	Type	Default	Description
file	file	-	Form file (PDF or image)
file_url	string	-	URL to form
field_data	string	-	JSON mapping field names to values
context	string	-	Additional context for field matching
confidence_threshold	float	0.5	Minimum confidence for matching (0-1)
page_range	string	-	Specific pages to process
skip_cache	bool	false	Skip cached results

Field Data Format

{
  "field_key": {
    "value": "The value to fill",
    "description": "Description to help match the field"
  }
}

Response

Field	Type	Description
status	string	Processing status
success	bool	Whether filling succeeded
output_format	string	pdf or png
output_base64	string	Base64-encoded filled form
fields_filled	array	Successfully filled field names
fields_not_found	array	Unmatched field names
page_count	int	Pages processed
cost_breakdown	object	Cost details

See Form Filling for more examples.

File Management

Upload and manage files for use in pipelines.

Upload File

Step 1: Request an upload URL

POST /api/v1/files/upload
Content-Type: application/json

{
  "filename": "document.pdf",
  "content_type": "application/pdf"
}

Response:

{
  "file_id": 123,
  "upload_url": "https://...",
  "reference": "datalab://file-abc123"
}

Step 2: Upload directly to the presigned URL

PUT {upload_url}
Content-Type: application/pdf

<file contents>

Step 3: Confirm upload

GET /api/v1/files/{file_id}/confirm

List Files

GET /api/v1/files?limit=50&offset=0

Get File Metadata

GET /api/v1/files/{file_id}

Get Download URL

GET /api/v1/files/{file_id}/download?expires_in=3600

Delete File

DELETE /api/v1/files/{file_id}

See File Management for detailed examples.

Thumbnails

Generate page thumbnails from a previously processed document:

GET /api/v1/thumbnails/{lookup_key}?thumb_width=300&page_range=0-2

Parameter	Type	Default	Description
lookup_key	string	Required	The request ID from a previous conversion
thumb_width	int	300	Thumbnail width in pixels
page_range	string	All pages	Pages to generate (e.g., "0,2-4")

Response:

{
  "success": true,
  "thumbnails": ["base64_encoded_jpg_1", "base64_encoded_jpg_2"]
}

Thumbnails are returned as base64-encoded JPG images.

Create Document

Generate DOCX files from markdown with track changes support:

POST /api/v1/create-document
Content-Type: application/json

{
  "markdown": "# Title\n\nThis is <ins data-revision-author=\"Editor\">newly added</ins> text.",
  "output_format": "docx"
}

See Create Document for detailed examples.

Webhooks

Configure webhooks to receive notifications when processing completes instead of polling.

Set a default webhook URL in your account settings, or override per-request with the webhook_url parameter.

See Webhooks for configuration details.

Rate Limits

Default rate limits apply per API key. If you exceed limits, you'll receive a 429 response.

See Rate Limits for details and how to request higher limits.

Next Steps

Use the Python SDK for a simpler integration with typed responses. Receive notifications when processing completes instead of polling. Understand file size limits, page limits, and rate limiting. Detailed guide to converting documents to Markdown, HTML, or JSON.

Documentation Index

Fetch the complete documentation index at: https://documentation.datalab.to/llms.txt Use this file to discover all available pages before exploring further.

[DEPRECATED] Marker

DEPRECATED: Use the new endpoints instead:

• /convert for document conversion
• /extract for structured data extraction
• /segment for document segmentation
• /custom-pipeline for custom pipeline execution

This endpoint will be removed in a future version.

OpenAPI

openapi: 3.1.0
info:
  title: Datalab API
  version: 0.0.1
servers:
  - url: https://www.datalab.to
    description: Datalab API
security: []
paths:
  /api/v1/marker:
    post:
      summary: '[DEPRECATED] Marker'
      description: |-
        **DEPRECATED**: Use the new endpoints instead:
        - `/convert` for document conversion
        - `/extract` for structured data extraction
        - `/segment` for document segmentation
        - `/custom-pipeline` for custom pipeline execution

        This endpoint will be removed in a future version.
      operationId: marker_api_v1_marker_post
      parameters:
        - name: wos-session
          in: cookie
          required: false
          schema:
            type: string
            title: Wos-Session
        - name: datalab_active_team
          in: cookie
          required: false
          schema:
            type: string
            title: Datalab Active Team
      requestBody:
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/Body_marker_api_v1_marker_post'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InitialResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      deprecated: true
      security:
        - APIKeyHeader: []
components:
  schemas:
    Body_marker_api_v1_marker_post:
      properties:
        file_url:
          anyOf:
            - type: string
            - type: 'null'
          title: File Url
          description: >-
            Optional file URL (http/https). If provided, the server will
            download and process it.
        mode:
          type: string
          title: Mode
          description: >-
            Which output mode to use. Valid values: 'fast' (lowest latency,
            great for real-time use cases), 'balanced' (balanced accuracy and
            latency, works well with most documents), 'accurate' (highest
            accuracy and latency, good on the most complex documents).
          default: fast
          choices:
            - fast
            - balanced
            - accurate
        max_pages:
          anyOf:
            - type: integer
            - type: 'null'
          title: Max Pages
          description: The maximum number of pages in the PDF to convert.
        page_range:
          anyOf:
            - type: string
            - type: 'null'
          title: Page Range
          description: >-
            The page range to parse, comma separated like 0,5-10,20. This will
            override max_pages if provided. Example: '0,2-4' will process pages
            0, 2, 3, and 4.
        langs:
          anyOf:
            - type: string
            - type: 'null'
          title: Langs
          description: >-
            Note: This parameter has been deprecated, and will be ignored in the
            current version.  The languages to use if OCR is needed, comma
            separated.  Must be either the names or codes from
            https://github.com/datalab-to/surya/blob/master/surya/languages.py. 
            Any other inputs will be ignored.
        force_ocr:
          type: boolean
          title: Force Ocr
          description: >-
            [DEPRECATED] This parameter is deprecated and has no effect. OCR is
            handled automatically by the parsing pipeline.
          default: false
          deprecated: true
        format_lines:
          type: boolean
          title: Format Lines
          description: >-
            [DEPRECATED] This parameter is deprecated and has no effect. Line
            formatting is handled automatically by the parsing pipeline.
          default: false
          deprecated: true
        paginate:
          type: boolean
          title: Paginate
          description: >-
            Whether to paginate the output.  Defaults to False.  If set to True,
            each page of the output will be separated by a horizontal rule that
            contains the page number (2 newlines, {PAGE_NUMBER}, 48 -
            characters, 2 newlines).
          default: false
        add_block_ids:
          type: boolean
          title: Add Block Ids
          description: >-
            Add data-block-id attributes to HTML elements for citation tracking.
            Only applies when output_format includes 'html'.
          default: false
        include_markdown_in_chunks:
          type: boolean
          title: Include Markdown In Chunks
          description: >-
            Include markdown field in chunks and JSON output. When enabled, each
            chunk will have a 'markdown' field with the markdown representation
            of that block. Only applies when output_format includes 'json' or
            'chunks'.
          default: false
        strip_existing_ocr:
          type: boolean
          title: Strip Existing Ocr
          description: >-
            [DEPRECATED] This parameter is deprecated and has no effect. OCR
            handling is managed automatically by the parsing pipeline.
          default: false
          deprecated: true
        disable_image_extraction:
          type: boolean
          title: Disable Image Extraction
          description: >-
            Disable image extraction from the PDF.  If use_llm is also set, then
            images will be automatically captioned.  Defaults to False.
          default: false
        disable_image_captions:
          type: boolean
          title: Disable Image Captions
          description: >-
            Disable synthetic image captions/descriptions in output. Images will
            be rendered as plain img tags without alt text or the
            img-description wrapper div. Defaults to False.
          default: false
        fence_synthetic_captions:
          type: boolean
          title: Fence Synthetic Captions
          description: >-
            Wrap synthetic image captions in markdown with HTML comment markers
            (<!-- BEGIN IMAGE CAPTION --> ... <!-- END IMAGE CAPTION -->) for
            easy identification/removal. Only applies to markdown output.
          default: false
        disable_ocr_math:
          type: boolean
          title: Disable Ocr Math
          description: >-
            [DEPRECATED] This parameter is deprecated and has no effect. Math
            recognition is handled automatically by the parsing pipeline.
          default: false
          deprecated: true
        use_llm:
          type: boolean
          title: Use Llm
          description: >-
            [DEPRECATED] This parameter is deprecated. Use the 'mode' parameter
            instead: 'balanced' or 'accurate' modes.
          default: false
          deprecated: true
        output_format:
          anyOf:
            - type: string
            - type: 'null'
          title: Output Format
          description: >-
            The output format for the text.  Can be 'json', 'html', 'markdown',
            or 'chunks'.  Defaults to 'markdown'.  You can comma separate
            multiple formats, like `markdown,html`.
        token_efficient_markdown:
          type: boolean
          title: Token Efficient Markdown
          description: >-
            When enabled, the markdown output uses token-efficient formatting
            optimized for LLMs (compact tables with single-dash headers,
            single-space list indents).
          default: false
        skip_cache:
          type: boolean
          title: Skip Cache
          description: >-
            Skip the cache and re-run the inference.  Defaults to False.  If set
            to True, the cache will be skipped and the inference will be re-run.
          default: false
        save_checkpoint:
          type: boolean
          title: Save Checkpoint
          description: >-
            Save the checkpoint after processing.  Defaults to False.  This is
            only useful if you're applying custom rules iteratively.
          default: false
        block_correction_prompt:
          anyOf:
            - type: string
            - type: 'null'
          title: Block Correction Prompt
          description: >-
            [DEPRECATED] This parameter is deprecated and has no effect. Block
            correction is not currently supported.
          deprecated: true
        page_schema:
          anyOf:
            - type: string
            - type: 'null'
          title: Page Schema
          description: >-
            The schema to use for structured extraction (only used with
            structured extraction endpoint). The ideal way to generate this is
            to create a Pydantic schema, then convert to JSON with
            .model_dump_json().
        segmentation_schema:
          anyOf:
            - type: string
            - type: 'null'
          title: Segmentation Schema
          description: >-
            The schema to use for document segmentation. Should be a JSON string
            containing segment names and descriptions for identifying page
            ranges of different document sections.
        additional_config:
          anyOf:
            - type: string
            - type: 'null'
          title: Additional Config
          description: >-
            Additional configuration options as a JSON string. Only these keys
            have effect: 'keep_pageheader_in_output' (bool),
            'keep_pagefooter_in_output' (bool), 'keep_spreadsheet_formatting'
            (bool).
        workflowstepdata_id:
          anyOf:
            - type: integer
            - type: 'null'
          title: Workflowstepdata Id
          description: >-
            Optional workflow step data ID. If provided, this request will be
            associated with the specified workflow step execution.
        extras:
          anyOf:
            - type: string
            - type: 'null'
          title: Extras
          description: >-
            Comma-separated list of extra features to enable. Currently
            supports: 'track_changes', 'chart_understanding',
            'table_row_bboxes', 'extract_links', 'infographic',
            'new_block_types'.
        webhook_url:
          anyOf:
            - type: string
            - type: 'null'
          title: Webhook Url
          description: >-
            Optional webhook URL to call when the request is complete. If
            provided, this will override the webhook URL stored in your account
            settings for this specific request.
        processing_location:
          anyOf:
            - type: string
            - type: 'null'
          title: Processing Location
          description: >-
            Optional residency region override (e.g. us, eu). When provided, use
            file_url or direct-upload; multipart uploads are rejected. When
            omitted, the request uses the team's configured residency and
            profile.
        pipeline_id:
          anyOf:
            - type: string
            - type: 'null'
          title: Pipeline Id
          description: >-
            Optional custom pipeline ID. If provided, will execute the custom
            pipeline configuration associated with this ID.
        run_eval:
          type: boolean
          title: Run Eval
          description: 'Internal: run evals over custom pipeline.'
          default: false
        model_override_settings:
          anyOf:
            - type: string
            - type: 'null'
          title: Model Override Settings
        word_bboxes:
          type: boolean
          title: Word Bboxes
          description: >-
            When enabled, predict per-word bounding boxes for each page and
            include them under page_info[id].metadata.words. Only supported by
            the Chandra parse pipeline.
          default: false
        file:
          anyOf:
            - type: string
              format: binary
            - type: 'null'
          title: File
          description: >-
            Input PDF, word document, powerpoint, or image file, uploaded as
            multipart form data.  Images must be png, jpg, or webp format.
      type: object
      title: Body_marker_api_v1_marker_post
    InitialResponse:
      properties:
        success:
          type: boolean
          title: Success
          description: Whether the request was successful.
          default: true
        error:
          anyOf:
            - type: string
            - type: 'null'
          title: Error
          description: >-
            If the request was not successful, this will contain an error
            message.
        request_id:
          type: string
          title: Request Id
          description: >-
            The ID of the request. This ID can be used to check the status of
            the request.
        request_check_url:
          type: string
          title: Request Check Url
          description: The URL to check the status of the request and get results.
        versions:
          anyOf:
            - additionalProperties: true
              type: object
            - type: string
            - type: 'null'
          title: Versions
          description: A dictionary of the versions of the libraries used in the request.
      type: object
      required:
        - request_id
        - request_check_url
      title: InitialResponse
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
              - type: string
              - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
        - loc
        - msg
        - type
      title: ValidationError
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      in: header
      name: X-API-Key

---

Documentation Index

Fetch the complete documentation index at: https://documentation.datalab.to/llms.txt Use this file to discover all available pages before exploring further.

[DEPRECATED] Table Recognition

[DEPRECATED] This endpoint is deprecated and will be removed in the future. This endpoint is used to submit a request for table recognition. The detected tables will be returned, as well as their parsed structure.

OpenAPI

openapi: 3.1.0
info:
  title: Datalab API
  version: 0.0.1
servers:
  - url: https://www.datalab.to
    description: Datalab API
security: []
paths:
  /api/v1/table_rec:
    post:
      summary: '[DEPRECATED] Table Recognition'
      description: >-
        [DEPRECATED] This endpoint is deprecated and will be removed in the
        future.

        This endpoint is used to submit a request for table recognition.  The
        detected tables will be returned, as well as their parsed structure.
      operationId: table_rec_api_v1_table_rec_post
      parameters:
        - name: wos-session
          in: cookie
          required: false
          schema:
            type: string
            title: Wos-Session
        - name: datalab_active_team
          in: cookie
          required: false
          schema:
            type: string
            title: Datalab Active Team
      requestBody:
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/Body_table_rec_api_v1_table_rec_post'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InitialResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      deprecated: true
      security:
        - APIKeyHeader: []
components:
  schemas:
    Body_table_rec_api_v1_table_rec_post:
      properties:
        max_pages:
          anyOf:
            - type: integer
            - type: 'null'
          title: Max Pages
          description: The maximum number of pages in the PDF to convert.
        page_range:
          anyOf:
            - type: string
            - type: 'null'
          title: Page Range
          description: >-
            The page range to parse, comma separated like 0,5-10,20. This will
            override max_pages if provided. Example: '0,2-4' will process pages
            0, 2, 3, and 4.
        output_format:
          anyOf:
            - type: string
            - type: 'null'
          title: Output Format
          description: >-
            The output format for the table.  Can be 'json', 'html', or
            'markdown'.  Defaults to 'markdown'.
        skip_cache:
          type: boolean
          title: Skip Cache
          description: >-
            Skip the cache and re-run the inference.  Defaults to False.  If set
            to True, the cache will be skipped and the inference will be re-run.
          default: false
        processing_location:
          anyOf:
            - type: string
            - type: 'null'
          title: Processing Location
          description: >-
            Optional residency region override (e.g. us, eu). When provided, use
            file_url or direct-upload; multipart uploads are rejected. When
            omitted, the request uses the team's configured residency and
            profile.
        paginate:
          type: boolean
          title: Paginate
          description: >-
            Whether to paginate the output.  Defaults to False.  If set to True,
            each page of the output will be separated by a horizontal rule that
            contains the page number (2 newlines, {PAGE_NUMBER}, 48 -
            characters, 2 newlines).
          default: false
        file:
          anyOf:
            - type: string
              format: binary
            - type: 'null'
          title: File
          description: >-
            Input PDF, word document, powerpoint, or image file, uploaded as
            multipart form data.  Images must be png, jpg, or webp format.
      type: object
      title: Body_table_rec_api_v1_table_rec_post
    InitialResponse:
      properties:
        success:
          type: boolean
          title: Success
          description: Whether the request was successful.
          default: true
        error:
          anyOf:
            - type: string
            - type: 'null'
          title: Error
          description: >-
            If the request was not successful, this will contain an error
            message.
        request_id:
          type: string
          title: Request Id
          description: >-
            The ID of the request. This ID can be used to check the status of
            the request.
        request_check_url:
          type: string
          title: Request Check Url
          description: The URL to check the status of the request and get results.
        versions:
          anyOf:
            - additionalProperties: true
              type: object
            - type: string
            - type: 'null'
          title: Versions
          description: A dictionary of the versions of the libraries used in the request.
      type: object
      required:
        - request_id
        - request_check_url
      title: InitialResponse
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
              - type: string
              - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
        - loc
        - msg
        - type
      title: ValidationError
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      in: header
      name: X-API-Key

---

Documentation Index

Fetch the complete documentation index at: https://documentation.datalab.to/llms.txt Use this file to discover all available pages before exploring further.

[DEPRECATED] OCR

[DEPRECATED] This endpoint is deprecated and will be removed in the future. This endpoint is used to submit a PDF or image for OCR. The OCR text lines will be returned, along with their bbox and polygon coordinates.

OpenAPI

openapi: 3.1.0
info:
  title: Datalab API
  version: 0.0.1
servers:
  - url: https://www.datalab.to
    description: Datalab API
security: []
paths:
  /api/v1/ocr:
    post:
      summary: '[DEPRECATED] OCR'
      description: >-
        [DEPRECATED] This endpoint is deprecated and will be removed in the
        future.

        This endpoint is used to submit a PDF or image for OCR.  The OCR text
        lines will be returned, along with their bbox and polygon coordinates.
      operationId: ocr_api_v1_ocr_post
      parameters:
        - name: wos-session
          in: cookie
          required: false
          schema:
            type: string
            title: Wos-Session
        - name: datalab_active_team
          in: cookie
          required: false
          schema:
            type: string
            title: Datalab Active Team
      requestBody:
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/Body_ocr_api_v1_ocr_post'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InitialResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      deprecated: true
      security:
        - APIKeyHeader: []
components:
  schemas:
    Body_ocr_api_v1_ocr_post:
      properties:
        max_pages:
          anyOf:
            - type: integer
            - type: 'null'
          title: Max Pages
          description: The maximum number of pages in the PDF to convert.
        page_range:
          anyOf:
            - type: string
            - type: 'null'
          title: Page Range
          description: >-
            The page range to parse, comma separated like 0,5-10,20. This will
            override max_pages if provided. Example: '0,2-4' will process pages
            0, 2, 3, and 4.
        langs:
          anyOf:
            - type: string
            - type: 'null'
          title: Langs
          description: >-
            Note: This parameter has been deprecated, and is no longer used. The
            languages to use for OCR, comma separated.  Can be up to 4
            languages. Must be either the names or codes from
            https://github.com/datalab-to/surya/blob/master/surya/languages.py. 
            Any other inputs will be ignored.  Defaults to 'en' if not provided.
        skip_cache:
          type: boolean
          title: Skip Cache
          description: >-
            Skip the cache and re-run the inference.  Defaults to False.  If set
            to True, the cache will be skipped and the inference will be re-run.
          default: false
        processing_location:
          anyOf:
            - type: string
            - type: 'null'
          title: Processing Location
          description: >-
            Optional residency region override (e.g. us, eu). When provided, use
            file_url or direct-upload; multipart uploads are rejected. When
            omitted, the request uses the team's configured residency and
            profile.
        file:
          anyOf:
            - type: string
              format: binary
            - type: 'null'
          title: File
          description: >-
            Input PDF, word document, powerpoint, or image file, uploaded as
            multipart form data.  Images must be png, jpg, or webp format.
      type: object
      title: Body_ocr_api_v1_ocr_post
    InitialResponse:
      properties:
        success:
          type: boolean
          title: Success
          description: Whether the request was successful.
          default: true
        error:
          anyOf:
            - type: string
            - type: 'null'
          title: Error
          description: >-
            If the request was not successful, this will contain an error
            message.
        request_id:
          type: string
          title: Request Id
          description: >-
            The ID of the request. This ID can be used to check the status of
            the request.
        request_check_url:
          type: string
          title: Request Check Url
          description: The URL to check the status of the request and get results.
        versions:
          anyOf:
            - additionalProperties: true
              type: object
            - type: string
            - type: 'null'
          title: Versions
          description: A dictionary of the versions of the libraries used in the request.
      type: object
      required:
        - request_id
        - request_check_url
      title: InitialResponse
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
              - type: string
              - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
        - loc
        - msg
        - type
      title: ValidationError
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      in: header
      name: X-API-Key

Documentation Index

Fetch the complete documentation index at: https://documentation.datalab.to/llms.txt Use this file to discover all available pages before exploring further.

Convert Document

Convert a PDF, image, or document to markdown, HTML, JSON, or chunks. Use save_checkpoint=true to save parsed state for later /extract or /segment calls.

OpenAPI

openapi: 3.1.0
info:
  title: Datalab API
  version: 0.0.1
servers:
  - url: https://www.datalab.to
    description: Datalab API
security: []
paths:
  /api/v1/convert:
    post:
      summary: Convert Document
      description: >-
        Convert a PDF, image, or document to markdown, HTML, JSON, or chunks.
        Use save_checkpoint=true to save parsed state for later /extract or
        /segment calls.
      operationId: convert_api_v1_convert_post
      parameters:
        - name: wos-session
          in: cookie
          required: false
          schema:
            type: string
            title: Wos-Session
        - name: datalab_active_team
          in: cookie
          required: false
          schema:
            type: string
            title: Datalab Active Team
      requestBody:
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/Body_convert_api_v1_convert_post'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InitialResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
        - APIKeyHeader: []
components:
  schemas:
    Body_convert_api_v1_convert_post:
      properties:
        file_url:
          anyOf:
            - type: string
            - type: 'null'
          title: File Url
          description: >-
            Optional file URL (http/https). If provided, the server will
            download and process it.
        mode:
          type: string
          title: Mode
          description: >-
            Which output mode to use. Valid values: 'fast' (lowest latency),
            'balanced' (balanced accuracy and latency), 'accurate' (highest
            accuracy).
          default: fast
          choices:
            - fast
            - balanced
            - accurate
          dashboard:
            description: Processing mode balancing speed and accuracy.
        max_pages:
          anyOf:
            - type: integer
            - type: 'null'
          title: Max Pages
          description: The maximum number of pages in the document to convert.
        page_range:
          anyOf:
            - type: string
            - type: 'null'
          title: Page Range
          description: >-
            The page range to convert, comma separated like 0,5-10,20. Overrides
            max_pages if provided.
          dashboard:
            description: >-
              Comma-separated page ranges to process, e.g. '0-2,4'. Leave empty
              for all pages.
        paginate:
          type: boolean
          title: Paginate
          description: >-
            Whether to paginate the output. Each page will be separated by a
            horizontal rule with the page number.
          default: false
          dashboard:
            description: Separate output by page with horizontal rules.
        add_block_ids:
          type: boolean
          title: Add Block Ids
          description: >-
            Add data-block-id attributes to HTML elements for citation tracking.
            Only applies when output_format includes 'html'.
          default: false
        include_markdown_in_chunks:
          type: boolean
          title: Include Markdown In Chunks
          description: Include markdown field in chunks and JSON output.
          default: false
        disable_image_extraction:
          type: boolean
          title: Disable Image Extraction
          description: Disable image extraction from the document.
          default: false
          dashboard: {}
        disable_image_captions:
          type: boolean
          title: Disable Image Captions
          description: Disable synthetic image captions/descriptions in output.
          default: false
          dashboard: {}
        word_bboxes:
          type: boolean
          title: Word Bboxes
          description: >-
            When enabled, predict per-word bounding boxes for each page and
            include them under page_info[id].metadata.words. Only supported by
            the Chandra parse pipeline.
          default: false
        fence_synthetic_captions:
          type: boolean
          title: Fence Synthetic Captions
          description: >-
            Wrap synthetic image captions with HTML comment markers for easy
            identification/removal.
          default: false
        output_format:
          anyOf:
            - type: string
            - type: 'null'
          title: Output Format
          description: >-
            The output format. Can be 'json', 'html', 'markdown', or 'chunks'.
            Defaults to 'markdown'. Comma separate multiple formats.
          dashboard:
            choices:
              - markdown
              - html
              - json
              - chunks
            description: Output format for the converted document.
            type: select
        token_efficient_markdown:
          type: boolean
          title: Token Efficient Markdown
          description: >-
            Optimize markdown for LLM token usage (compact tables, single-space
            indents).
          default: false
        skip_cache:
          type: boolean
          title: Skip Cache
          description: Skip the cache and re-run the conversion.
          default: false
          dashboard:
            description: Skip cache and re-run processing.
        save_checkpoint:
          type: boolean
          title: Save Checkpoint
          description: >-
            Save a checkpoint after conversion. The checkpoint_id in the
            response can be used with /extract or /segment to skip re-parsing.
          default: false
          dashboard:
            description: Save a checkpoint for later /extract or /segment calls.
        additional_config:
          anyOf:
            - type: string
            - type: 'null'
          title: Additional Config
          description: >-
            Additional configuration as a JSON string. Supported keys:
            'keep_pageheader_in_output', 'keep_pagefooter_in_output',
            'keep_spreadsheet_formatting'.
        workflowstepdata_id:
          anyOf:
            - type: integer
            - type: 'null'
          title: Workflowstepdata Id
          description: Optional workflow step data ID to associate with this request.
        extras:
          anyOf:
            - type: string
            - type: 'null'
          title: Extras
          description: >-
            Comma-separated list of extra features: 'track_changes',
            'chart_understanding', 'table_row_bboxes', 'extract_links',
            'infographic', 'new_block_types'.
          dashboard:
            description: >-
              Comma-separated feature flags: chart_understanding, infographic,
              extract_links, table_row_bboxes, new_block_types.
        webhook_url:
          anyOf:
            - type: string
            - type: 'null'
          title: Webhook Url
          description: Optional webhook URL to call when the request is complete.
        processing_location:
          anyOf:
            - type: string
            - type: 'null'
          title: Processing Location
          description: >-
            Optional residency region override (e.g. us, eu). When provided, use
            file_url or direct-upload; multipart uploads are rejected. When
            omitted, the request uses the team's configured residency and
            profile.
        eval_rubric_id:
          anyOf:
            - type: integer
            - type: 'null'
          title: Eval Rubric Id
          description: Optional eval rubric ID to run evaluation after conversion.
        force_new:
          type: boolean
          title: Force New
          description: 'Internal: force Modal backend.'
          default: false
        model_override_settings:
          anyOf:
            - type: string
            - type: 'null'
          title: Model Override Settings
        file:
          anyOf:
            - type: string
              format: binary
            - type: 'null'
          title: File
          description: >-
            Input PDF, word document, powerpoint, or image file, uploaded as
            multipart form data.  Images must be png, jpg, or webp format.
      type: object
      title: Body_convert_api_v1_convert_post
    InitialResponse:
      properties:
        success:
          type: boolean
          title: Success
          description: Whether the request was successful.
          default: true
        error:
          anyOf:
            - type: string
            - type: 'null'
          title: Error
          description: >-
            If the request was not successful, this will contain an error
            message.
        request_id:
          type: string
          title: Request Id
          description: >-
            The ID of the request. This ID can be used to check the status of
            the request.
        request_check_url:
          type: string
          title: Request Check Url
          description: The URL to check the status of the request and get results.
        versions:
          anyOf:
            - additionalProperties: true
              type: object
            - type: string
            - type: 'null'
          title: Versions
          description: A dictionary of the versions of the libraries used in the request.
      type: object
      required:
        - request_id
        - request_check_url
      title: InitialResponse
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
              - type: string
              - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
        - loc
        - msg
        - type
      title: ValidationError
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      in: header
      name: X-API-Key

---

Documentation Index

Fetch the complete documentation index at: https://documentation.datalab.to/llms.txt Use this file to discover all available pages before exploring further.

Marker Result Check

Poll this endpoint to check status of Marker request and retrieve final results

OpenAPI

openapi: 3.1.0
info:
  title: Datalab API
  version: 0.0.1
servers:
  - url: https://www.datalab.to
    description: Datalab API
security: []
paths:
  /api/v1/marker/{request_id}:
    get:
      summary: Marker Result Check
      description: >-
        Poll this endpoint to check status of Marker request and retrieve final
        results
      operationId: result_response_api_v1_marker__request_id__get
      parameters:
        - name: request_id
          in: path
          required: true
          schema:
            type: string
            title: Request Id
        - name: wos-session
          in: cookie
          required: false
          schema:
            type: string
            title: Wos-Session
        - name: datalab_active_team
          in: cookie
          required: false
          schema:
            type: string
            title: Datalab Active Team
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/MarkerFinalResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
        - APIKeyHeader: []
components:
  schemas:
    MarkerFinalResponse:
      properties:
        status:
          type: string
          title: Status
          description: >-
            The status of the request. Should be 'complete' when the request is
            done.
        result_url:
          anyOf:
            - type: string
            - type: 'null'
          title: Result Url
          description: >-
            Signed URL for downloading the completed result JSON when direct
            result download is required.
        expires_in:
          anyOf:
            - type: integer
            - type: 'null'
          title: Expires In
          description: Number of seconds until result_url expires.
        output_format:
          type: string
          title: Output Format
          description: The format of the output.  'markdown' or 'json'.
        chunks:
          anyOf:
            - additionalProperties: true
              type: object
            - type: string
            - type: 'null'
          title: Chunks
          description: >-
            The output in chunks format.  The top-level key 'blocks' contains a
            list of blocks from the document with metadata.
        json:
          anyOf:
            - additionalProperties: true
              type: object
            - type: string
            - type: 'null'
          title: Json
          description: The JSON representation of the PDF if the output format is 'json'.
        markdown:
          anyOf:
            - type: string
            - type: 'null'
          title: Markdown
          description: >-
            The markdown representation of the PDF if the output format is
            'markdown'.
        html:
          anyOf:
            - type: string
            - type: 'null'
          title: Html
          description: The HTML representation of the PDF if the output format is 'html'.
        extraction_schema_json:
          anyOf:
            - type: string
            - type: 'null'
          title: Extraction Schema Json
          description: >-
            The output of a marker extraction request containing the filled in
            extraction schema.
        extraction_score_average:
          anyOf:
            - type: number
            - type: 'null'
          title: Extraction Score Average
          description: >-
            Average confidence score (1-5) across all extracted fields, when
            scoring is applied.
        extraction_mode:
          anyOf:
            - type: string
            - type: 'null'
          title: Extraction Mode
          description: 'The extraction mode used for this request: ''fast'' or ''balanced''.'
        segmentation_results:
          anyOf:
            - additionalProperties: true
              type: object
            - type: 'null'
          title: Segmentation Results
          description: >-
            Results of document segmentation showing page ranges for each
            identified segment. Contains segment names, page ranges, and
            confidence levels (high/medium/low).
        images:
          anyOf:
            - additionalProperties:
                type: string
              type: object
            - type: 'null'
          title: Images
          description: >-
            A dictionary of the images in the PDF, where the key is the filename
            for the image, and the value is the base64 encoded image.  Images
            should be stored in the same directory as the PDF.
        metadata:
          anyOf:
            - additionalProperties: true
              type: object
            - type: 'null'
          title: Metadata
          description: A dictionary of metadata about the PDF and the conversion process.
        success:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Success
          description: Whether the conversion was successful.
        error:
          anyOf:
            - type: string
            - type: 'null'
          title: Error
          description: >-
            If the conversion was not successful, this will contain an error
            message.
        parse_quality_score:
          anyOf:
            - type: number
            - type: 'null'
          title: Parse Quality Score
          description: The parse quality score of the output, if available.
        page_count:
          anyOf:
            - type: integer
            - type: 'null'
          title: Page Count
          description: The number of pages that were converted.
        total_cost:
          anyOf:
            - type: integer
            - type: 'null'
          title: Total Cost
          description: The total cost of the conversion.
          deprecated: true
        cost_breakdown:
          anyOf:
            - additionalProperties: true
              type: object
            - type: 'null'
          title: Cost Breakdown
          description: >-
            A dictionary of the cost breakdown of this request. Includes the
            list cost without discounts and final cost to clients after any
            discounts (e.g. for opting into model training).
        runtime:
          anyOf:
            - type: number
            - type: 'null'
          title: Runtime
          description: The runtime of the conversion.
        checkpoint_id:
          anyOf:
            - type: string
            - type: 'null'
          title: Checkpoint Id
          description: >-
            The ID of the checkpoint that was created for this conversion.  This
            can be used to retrieve the checkpoint later.
        versions:
          anyOf:
            - additionalProperties: true
              type: object
            - type: string
            - type: 'null'
          title: Versions
          description: A dictionary of the versions of the libraries used in the request.
        evaluation:
          anyOf:
            - $ref: '#/components/schemas/EvaluationResults'
            - type: 'null'
          description: >-
            Evaluation results, when available, for requests that run
            evaluation. Contains per-rule scores for validating custom pipeline
            behavior.
      type: object
      required:
        - status
      title: MarkerFinalResponse
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    EvaluationResults:
      properties:
        eval_definition_name:
          type: string
          title: Eval Definition Name
          description: Name of the evaluation definition
        evaluations:
          items:
            $ref: '#/components/schemas/EvaluationRuleSummary'
          type: array
          title: Evaluations
          description: Per-rule evaluation summaries
        total_items_evaluated:
          type: integer
          title: Total Items Evaluated
          description: Total number of items evaluated across all rules
      type: object
      required:
        - eval_definition_name
        - evaluations
        - total_items_evaluated
      title: EvaluationResults
      description: Container for evaluation results.
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
              - type: string
              - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
        - loc
        - msg
        - type
      title: ValidationError
    EvaluationRuleSummary:
      properties:
        name:
          type: string
          title: Name
          description: Name of the evaluation rule
        type:
          type: string
          title: Type
          description: 'Type of evaluation: block, page, or document'
        rule_score:
          type: number
          title: Rule Score
          description: Aggregated score for this rule (0-5)
        items_evaluated:
          type: integer
          title: Items Evaluated
          description: Number of items evaluated
        individual_results:
          items:
            additionalProperties: true
            type: object
          type: array
          title: Individual Results
          description: >-
            Bottom-k lowest scoring individual results with score, feedback,
            block_id, page_id, block_type
      type: object
      required:
        - name
        - type
        - rule_score
        - items_evaluated
      title: EvaluationRuleSummary
      description: Summary of a single evaluation rule result.
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      in: header
      name: X-API-Key

Documentation Index

Fetch the complete documentation index at: https://documentation.datalab.to/llms.txt Use this file to discover all available pages before exploring further.

OCR Result Check

Poll this endpoint to check status of an OCR request and retrieve final results

OpenAPI

openapi: 3.1.0
info:
  title: Datalab API
  version: 0.0.1
servers:
  - url: https://www.datalab.to
    description: Datalab API
security: []
paths:
  /api/v1/ocr/{request_id}:
    get:
      summary: OCR Result Check
      description: >-
        Poll this endpoint to check status of an OCR request and retrieve final
        results
      operationId: result_response_api_v1_ocr__request_id__get
      parameters:
        - name: request_id
          in: path
          required: true
          schema:
            type: string
            title: Request Id
        - name: wos-session
          in: cookie
          required: false
          schema:
            type: string
            title: Wos-Session
        - name: datalab_active_team
          in: cookie
          required: false
          schema:
            type: string
            title: Datalab Active Team
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OCRFinalResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
        - APIKeyHeader: []
components:
  schemas:
    OCRFinalResponse:
      properties:
        status:
          type: string
          title: Status
          description: >-
            The status of the request. Should be 'complete' when the request is
            done.
        result_url:
          anyOf:
            - type: string
            - type: 'null'
          title: Result Url
          description: >-
            Signed URL for downloading the completed result JSON when direct
            result download is required.
        expires_in:
          anyOf:
            - type: integer
            - type: 'null'
          title: Expires In
          description: Number of seconds until result_url expires.
        pages:
          anyOf:
            - items:
                additionalProperties: true
                type: object
              type: array
            - type: 'null'
          title: Pages
          description: >-
            The detected OCR text on each page.  Each page will have the bboxes
            and detected text within each line.
        success:
          anyOf:
            - type: boolean
            - type: 'null'
          title: Success
          description: Whether the conversion was successful.
        error:
          anyOf:
            - type: string
            - type: 'null'
          title: Error
          description: >-
            If the conversion was not successful, this will contain an error
            message.
        page_count:
          anyOf:
            - type: integer
            - type: 'null'
          title: Page Count
          description: The number of pages that had ocr run on them.
        total_cost:
          anyOf:
            - type: integer
            - type: 'null'
          title: Total Cost
          description: The total cost of the conversion.
          deprecated: true
        cost_breakdown:
          anyOf:
            - additionalProperties: true
              type: object
            - type: 'null'
          title: Cost Breakdown
          description: >-
            A dictionary of the cost breakdown of this request. Includes the
            list cost without discounts and final cost to clients after any
            discounts (e.g. for opting into model training).
        versions:
          anyOf:
            - additionalProperties: true
              type: object
            - type: string
            - type: 'null'
          title: Versions
          description: A dictionary of the versions of the libraries used in the request.
      type: object
      required:
        - status
      title: OCRFinalResponse
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
              - type: string
              - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
        - loc
        - msg
        - type
      title: ValidationError
  securitySchemes:
    APIKeyHeader:
      type: apiKey
      in: header
      name: X-API-Key