MarketAIVerse Extract API

The Extract API from MarketAIVerse — 2 operation(s) for extract.

GitHub OpenAPI

Operations 3

GET /api/v1/extract How the extraction works, its limits and privacy #
POST /api/v1/extract Send a PDF, scan or photo; get its tables and fields #
GET /api/v1/extract/{job_id} The state or result of an extraction job #

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/marketaiverse-com:marketaiverse-com-extract-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

marketaiverse-com-extract-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: MarketAIVerse Extract API
  version: 1.0.0
  summary: A neutral marketplace for AI models, agents, tools and datasets.
  description: 'Everything here is readable without an account or a key. The house rule is that no product carries a number unless we measured it: where no benchmark exists, the field is absent and the label says so. Endpoints that change anything need a session, and a seller can never move their own listing onto the shelf.'
  contact:
    url: https://marketaiverse.com
servers:
- url: https://marketaiverse.com
tags:
- name: Extract
paths:
  /api/v1/extract:
    get:
      summary: How the extraction works, its limits and privacy
      responses:
        '200':
          description: The rules, as JSON.
      tags:
      - Extract
      operationId: getApiV1Extract
      x-operation-id-source: derived
    post:
      summary: Send a PDF, scan or photo; get its tables and fields
      description: 'Send ONE of: multipart `file`, JSON `url` (public http/https only), JSON `file_base64`, or the raw file with Content-Type application/pdf or image/*. Returns 202 with a `job_id`; poll GET /api/v1/extract/{job_id}. Up to 10 MB and 10 pages, 20 documents a day per address, free in beta. The file is deleted once read and the result after 24 hours.'
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                file:
                  type: string
                  format: binary
              required:
              - file
          application/json:
            schema:
              type: object
              properties:
                url:
                  type: string
                  description: Public address of the document.
                file_base64:
                  type: string
                  description: The document, base64.
            example:
              url: https://example.com/invoice.pdf
      responses:
        '202':
          description: Queued; poll the job.
        '400':
          description: No file, not a PDF or image, or a bad url.
        '413':
          description: Larger than 10 MB.
        '429':
          description: Daily limit for this address reached.
        '503':
          description: Queue full; retry in a minute.
      tags:
      - Extract
      operationId: postApiV1Extract
      x-operation-id-source: derived
  /api/v1/extract/{job_id}:
    get:
      summary: The state or result of an extraction job
      description: '`state` is queued, working, done or error. When done: `pages` (each with `method` text or ocr, `text`, `tables` as rows, `fields` as label/value pairs, and `ocr_confidence` for scans) and `tables_csv`. Add ?format=csv&table=N for one table as plain CSV.'
      parameters:
      - name: job_id
        in: path
        required: true
        schema:
          type: string
      - name: format
        in: query
        schema:
          type: string
          enum:
          - csv
      - name: table
        in: query
        schema:
          type: integer
      responses:
        '200':
          description: The job.
        '404':
          description: No such job, or deleted after 24 hours.
      tags:
      - Extract
      operationId: getApiV1ExtractByJobId
      x-operation-id-source: derived
x-labels:
  MEASURED: measured; a machine and a date are attached
  COMPUTED: computed from a measurement; the formula is published
  NOT_MEASURED: no measurement exists, so no number is published
x-states:
- draft
- sent
- being_measured
- on_shelf
- turned_down
x-rule: Only the market can move a listing to 'on_shelf', and only when at least one measurement is attached to it. A seller can go no further than 'sent'.