AI Inference · x402 · early usage

Extract all text from a PDF

Extract all text from a PDF. Send as pdf_base64 (base64-encoded PDF, max ~10 MB decoded). Returns text (full concatenated text), pages array (per-page text + char_count), page_count, and metadata (title, author, creator). Encode with: Buffer.from(pdfBytes).to…

by agentsvc.io · discovered, not yet claimed by its owner · updated 2026-10-11

30d calls8
30d payers1
MethodPOST
Outputjson

Mirrored from Coinbase's public x402 Bazaar. The description is the provider's own text and has not been reviewed here; the payment requirements are copied as published.

What it does

Extract all text from a PDF. Send as pdf_base64 (base64-encoded PDF, max ~10 MB decoded). Returns text (full concatenated text), pages array (per-page text + char_count), page_count, and metadata (title, author, creator). Encode with: Buffer.from(pdfBytes).toString('base64'). Ideal for RAG pipelines, document QA, or LLM ingestion.

Tags: pdf · text · extract · parse · document · bazaar · builder-code

Call contract

Method
POST
Input
json
Output
json
Last paid call
2026-10-11
Input example from Bazaar metadata
{
  "max_pages": 10,
  "pdf_base64": "<base64 of a PDF>"
}
Output example
{
  "data": {
    "extracted_at": "2026-04-10T14:00:00.000Z",
    "file_size_bytes": 245760,
    "metadata": {
      "author": "Finance Department",
      "creator": "Adobe Acrobat",
      "title": "Q1 2026 Financial Report"
    },
    "page_count": 12,
    "pages": [
      {
        "char_count": 54,
        "page": 1,
        "text": "Quarterly Financial Report Q1 2026\n\nExecutive Summary"
      },
      {
        "char_count": 58,
        "page": 2,
        "text": "Table of Contents\n1. Revenue Overview\n2. Cost Analysis"
      }
    ],
    "text": "Quarterly Financial Report Q1 2026\n\nExecutive Summary\nTotal revenue increased by 23% year-over-year..."
  },
  "success": true
}

Use with an agent

  1. Discover. Agents find this listing with GET https://bazaar.saylorinnovations.com/discovery/search?query=…, the MCP tool search_resources, or /discovery/resources.
  2. Inspect. Fetch /resources/35722.json for the price and payment options.
  3. Pay. Call GET https://agentsvc.io/api/v1/proxy/pdf-extract. The provider answers 402 with its payment requirements. An x402 client signs one of the options below and retries with PAYMENT-SIGNATURE.
  4. Execute. The provider returns 200 with the data. Agent Bazaar is not in the request path and never sees your payment.

For humans

You don't need an account or an API key; you need a wallet holding a small amount of USDC on Base, Solana, Polygon, Arbitrum One, and an x402-capable client (see the examples below). Call the endpoint unpaid first to see exactly what it asks for.

Pricing & payment

Price
$0.0055 / request
Protocol
x402 v2
Auth
No account or API key. Pay per request.
Networks
Base, Solana, Polygon, Arbitrum One
Demand
8 calls · 1 unique payers in 30d (public x402 Bazaar data)

x402 payment requirements

SchemeNetworkAssetAmountPay toTimeout
exactBase
eip155:8453
USDC$0.00550x622efA6Ceb83a5b6EdBC931332f4db68B7f74F27300s
exactSolana
solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp
USDC$0.00555JzPS5qpEwUM1vTC9GG7uqvwJdHzbEwfoPHf2Ki977tg300s
exactPolygon
eip155:137
USDC$0.00550x622efA6Ceb83a5b6EdBC931332f4db68B7f74F27300s
exactArbitrum One
eip155:42161
USDC$0.00550x622efA6Ceb83a5b6EdBC931332f4db68B7f74F27300s
accepts[] (raw JSON)
[
  {
    "scheme": "exact",
    "network": "eip155:8453",
    "payTo": "0x622efA6Ceb83a5b6EdBC931332f4db68B7f74F27",
    "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
    "amount": "5500",
    "amountUsd": 0.0055,
    "maxTimeoutSeconds": 300
  },
  {
    "scheme": "exact",
    "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
    "payTo": "5JzPS5qpEwUM1vTC9GG7uqvwJdHzbEwfoPHf2Ki977tg",
    "asset": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
    "amount": "5500",
    "amountUsd": 0.0055,
    "maxTimeoutSeconds": 300
  },
  {
    "scheme": "exact",
    "network": "eip155:137",
    "payTo": "0x622efA6Ceb83a5b6EdBC931332f4db68B7f74F27",
    "asset": "0x3c499c542cEF5E3811e1192ce70d8cC03d5c3359",
    "amount": "5500",
    "amountUsd": 0.0055,
    "maxTimeoutSeconds": 300
  },
  {
    "scheme": "exact",
    "network": "eip155:42161",
    "payTo": "0x622efA6Ceb83a5b6EdBC931332f4db68B7f74F27",
    "asset": "0xaf88d065e77c8cC2239327C5EDb3A432268e5831",
    "amount": "5500",
    "amountUsd": 0.0055,
    "maxTimeoutSeconds": 300
  }
]

Schemas

Output schema (JSON Schema)
{
  "properties": {
    "example": {
      "properties": {
        "data": {
          "properties": {
            "extracted_at": {
              "description": "ISO 8601 timestamp of extraction",
              "format": "date-time",
              "type": "string"
            },
            "file_size_bytes": {
              "description": "Size of the decoded PDF in bytes",
              "type": "integer"
            },
            "metadata": {
              "description": "PDF document metadata (if available)",
              "properties": {
                "author": {
                  "type": "string"
                },
                "creation_date": {
                  "type": "string"
                },
                "creator": {
                  "type": "string"
                },
                "producer": {
                  "type": "string"
                },
                "subject": {
                  "type": "string"
                },
                "title": {
                  "type": "string"
                }
              },
              "type": "object"
            },
            "page_count": {
              "description": "Total number of pages in the PDF",
              "type": "integer"
            },
            "pages": {
              "description": "Per-page text content (first max_pages pages)",
              "items": {
                "properties": {
                  "char_count": {
                    "description": "Number of characters on this page",
                    "type": "integer"
                  },
                  "page": {
                    "description": "Page number (1-based)",
                    "type": "integer"
                  },
                  "text": {
                    "description": "Extracted text for this page",
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "type": "array"
            },
            "text": {
              "description": "Full extracted text from all pages, joined with newlines. Preserves paragraph structure where possible.",
              "type": "string"
            }
          },
          "required": [
            "text",
            "page_count",
            "extracted_at"
          ],
          "type": "object"
        },
        "success": {
          "type": "boolean"
        }
      },
      "required": [
        "success",
        "data"
      ],
      "type": "object"
    },
    "type": {
      "type": "string"
    }
  },
  "required": [
    "type"
  ],
  "type": "object"
}
Example shape — generated from the schema, not a captured live response
{
  "example": {
    "data": {
      "extracted_at": "2026-01-01T00:00:00Z",
      "file_size_bytes": 0,
      "metadata": {
        "author": "string",
        "creation_date": "string",
        "creator": "string",
        "producer": "string",
        "subject": "string",
        "title": "string"
      },
      "page_count": 0,
      "pages": [
        {
          "char_count": 0,
          "page": 0,
          "text": "string"
        }
      ],
      "text": "string"
    },
    "success": true
  },
  "type": "string"
}

Examples

curl
curl "https://agentsvc.io/api/v1/proxy/pdf-extract"
# -> 402 Payment Required, accepts[] lists how to pay
# retry with a PAYMENT-SIGNATURE (or PAYMENT header) once paid
JavaScript
const res = await fetch("https://agentsvc.io/api/v1/proxy/pdf-extract");
if (res.status === 402) {
  const { accepts } = await res.json();
  // pay one of accepts[] via an x402 client, then retry with the payment header
}
Python
import httpx
res = httpx.get("https://agentsvc.io/api/v1/proxy/pdf-extract")
if res.status_code == 402:
    accepts = res.json()["accepts"]
    # pay one of accepts[] via an x402 client, then retry with the payment header

Details

Provider
agentsvc.io
Endpoint
https://agentsvc.io/api/v1/proxy/pdf-extract
Machine-readable
/resources/35722.json