agentutility(7)$ man pdf-extract-tables
/pdf-extract-tables
PRICE / CALL
$0.10
USDC · base mainnet · scheme: exact
METHOD
POST
CLUSTER
mediakitCATEGORY
uncategorized
STATUS
● live
NAME
pdf-extract-tables — extracts every table from a pdf, digital or scanned, and returns row-by-column text matrices page-by-page
SYNOPSIS
POST https://x402.agentutility.ai/pdf-extract-tables
Content-Type: application/json
X-PAYMENT: <signed-transferWithAuthorization>
{ ... }↳ first call →
402 Payment Required. Sign USDCtransferWithAuthorization, retry with theX-PAYMENT header.DESCRIPTION
Extracts every table from a PDF, digital or scanned, and returns row-by-column text matrices page-by-page. AI + OCR pipeline with optional cell bounding boxes for downstream layout reconstruction and an optional page_range filter ('1-5', '3', '1,3,5'). Handles merged headers, multi-page financial statements, balance sheets, lab results, scanned reports. 30 pages max. Sibling of pdf-to-markdown using the same Datalab backend, but pre-parsed to tables only. Use it as a PDF table extractor, scanned-table parser, financial-table OCR, multi-page table consolidator, or Datalab Marker tables endpoint.
INPUT — request schema
| property | type | description | req? |
|---|---|---|---|
| pdf_url | string | Public URL of a PDF file (http or https). Must be directly fetchable, not behind auth or a viewer redirect. Max 30 pages. | required |
| page_range | string | Optional 1-indexed page filter applied after extraction. Accepts ranges, single pages, or comma-lists: '1-5', '3', '1,3,5'. Default: all pages. | optional |
OUTPUT — response shape
| field | type | description |
|---|---|---|
| source_url | string | Echoes back the PDF URL that was extracted, for traceability. |
| page_count | string | Total number of pages in the input PDF (capped at 30). |
| tables | string | Array of detected tables with page number, row × column text matrix, and optional cell bounding boxes. |
| source | string | Backend identifier, typically 'datalab-marker', indicating the OCR/parsing engine used. |
EXAMPLES — two ways to call
EXAMPLE 1 · curl
curl -X POST https://x402.agentutility.ai/pdf-extract-tables \
-H 'Content-Type: application/json' \
-d '{ }'first response =
402 Payment Required with payment requirements; sign + retry with X-PAYMENT.EXAMPLE 2 · mcp
# Install the MCP package for this endpoint's cluster npx -y @agentutility/mcp-<cluster> # Required: EVM private key with USDC on Base export X402_PRIVATE_KEY=0x... # Then call the pdf-extract-tables tool from your MCP-aware agent.
MCP server handles payment automatically — your coding agent just calls the tool by name.
METADATA
- tags
- pdftable-extractionocrmediakitdocument-parsingfinancial-tablesdatalabpdf-tables
- methods
- POST
- cluster
- mediakit
- price
- $0.10 USDC per call
ADJACENT — other endpoints in mediakit
| endpoint | description | price |
|---|---|---|
| doc-to-json | Converts any document (PDF, DOCX, PPT, XLSX, or image) into structured JSON matching a caller-supplied schema. | $0.10 |
| extract-tables | Detects and extracts every table from a PDF document, returning structured JSON or CSV per table. | $0.10 |
| pdf-table-extract | Extracts tables from digital or scanned PDFs, returning row/column matrices, CSV output, page numbers, and optional cell boxes. | $0.10 |
| pdf-table-extractor | Finds tables in digital or scanned PDFs and returns row-by-column matrices, page numbers, and optional cell bounding boxes. | $0.10 |
| pdf-to-jpg | Converts a PDF to JPG, PNG, or WEBP images, rendering every page at configurable DPI (36-600) and returning one image URL per page. | $0.10 |
| speaker-diarize | Speaker diarization / who-said-what transcription. | $0.10 |
| transcribe | Transcribe video to text. | $0.10 |
| video-summarize | Summarizes videos, podcasts, and lectures in one call: Whisper v3 transcribes, then Mistral summarizes. | $0.10 |
SEE ALSO