agentutility(7)$ man doc-to-json
/doc-to-json
PRICE / CALL
$0.10
USDC · base mainnet · scheme: exact
METHOD
POST
CLUSTER
mediakitCATEGORY
uncategorized
STATUS
● live
NAME
doc-to-json — document to structured json / pdf/docx/ppt/xlsx/image to json / file parser with schema / invoice extractor / resume parser / contract ex…
SYNOPSIS
POST https://x402.agentutility.ai/doc-to-json
Content-Type: application/json
X-PAYMENT: <signed-transferWithAuthorization>
{ ... }↳ first call →
402 Payment Required. Sign USDCtransferWithAuthorization, retry with theX-PAYMENT header.DESCRIPTION
Document to structured JSON / PDF/DOCX/PPT/XLSX/image to JSON / file parser with schema / invoice extractor / resume parser / contract extractor / RFP parser / receipt extractor / form data extraction. Converts any document (CloudConvert) to plain text, then runs Morpheus mistral-31-24b with strict json_schema response_format to force the output to a caller-supplied schema. OCR-aware for images and scanned PDFs.
INPUT — request schema
| property | type | description | req? |
|---|---|---|---|
| file_url | string | Public URL of the file. Max 25MB. Supports PDF, DOCX, DOC, PPT, PPTX, XLSX, XLS, ODT, RTF, TXT, HTML, MD, JPG, PNG, GIF, TIFF, WEBP. | required |
| schema | object | JSON schema describing expected output. Must include 'properties'. | required |
| instructions | string | Optional extra extraction guidance. | optional |
| ocr | boolean | Force OCR. Defaults to true for images, false for text-native formats. | optional |
OUTPUT — response shape
| field | type | description |
|---|---|---|
| file_url | string | — |
| source_format | string | — |
| text_chars | string | — |
| extracted | string | — |
| model | string | — |
EXAMPLES — two ways to call
EXAMPLE 1 · curl
curl -X POST https://x402.agentutility.ai/doc-to-json \
-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 doc-to-json tool from your MCP-aware agent.
MCP server handles payment automatically — your coding agent just calls the tool by name.
METADATA
- tags
- mediakitdoctojsondoc-to-json
- methods
- POST
- cluster
- mediakit
- price
- $0.10 USDC per call
ADJACENT — other endpoints in mediakit
| endpoint | description | price |
|---|---|---|
| extract-tables | Extract tables from PDF / table extractor / PDF to CSV / spreadsheet from PDF. | $0.10 |
| mp4-to-mp3 | MP4 to MP3 audio extractor. | $0.10 |
| mp4-to-mp3-api | MP4 to MP3 API / video to MP3 converter / extract audio from video. | $0.10 |
| pdf-extract-tables | PDF table extractor / table from PDF / scanned-table parsing / financial-table OCR / multi-page table consolidator / Datalab Marker tables. | $0.10 |
| pdf-table-extractor | PDF table extractor / extract tables from PDF / scanned table OCR. | $0.10 |
| pdf-to-jpg | PDF to JPG / PNG / WEBP image converter. | $0.10 |
| speaker-diarize | Speaker diarization / who-said-what transcription. | $0.10 |
| transcribe | Transcribe video to text. | $0.10 |
SEE ALSO