Sumble / Find or enrich companies

Sumble tool sumble-organizations on looot: input fields, $0.03 per call, output shape, and code to run it with curl, JavaScript or Python.

Unified organizations endpoint. For a SINGLE known company, pass organizations (a list of {id} or {name/url/location} matchers, e.g. {“url”: “stripe.com”} – bare domain, no https:// prefix) – NOT filter. filter.query is an advanced search DSL for finding organizations matching job/tech evidence (e.g. “technology EQ ‘react’”), not a company lookup field, and a bare domain there returns a 400. select is always required (may be {} for id-only).

Tool id: sumble-organizations
Provider: Sumble
Job: Get organizations (organizations.get)
Price: $0.03 per call. A call that fails at the provider costs $0.

Inputs

Name	Type	Required	Description
`filter`	object	no
`include_closed`	boolean	no	Filter mode only: include organizations marked permanently closed (`status` = ‘closed’) in the results, they are excluded by default. Request the `status` / `status_reason` attributes to identify which results are closed. Not valid with `organizations` (direct lookups always resolve closed organizations).
`limit`	integer	no	Maximum number of results to return.
`match_source`	string	no	Filter mode only. Which evidence an organization may match the `filter` on. `any` (default) matches on either job posts or the skills its employees list on LinkedIn/Coresignal. `job_post` restricts matches to job-post evidence only, so an org that matches solely because an employee lists the technology (with no job posts mentioning it) is excluded. Applies to all job-side filters (technology, job function, hiring location, etc.).
`offset`	integer	no	Number of results to skip.
`order_by_advanced_query`	string	no
`order_by_column`	string	no
`order_by_direction`	string	no
`order_by_job_function`	string	no
`organizations`	array	yes	Direct lookup by known company identifiers. Each item: {id} (Sumble id) OR {name, url, location} (url is a bare domain, e.g. ‘stripe.com’, no protocol). Use this for a single known company instead of filter.query.
`select`	object	yes

Output

Shape of the run’s result, checked against 1 real answer:

{ id, total, credits_used, matched_count, organizations: { input: { url }, entities: unknown[], attributes: { id, url, name, industry, employee_count } }[], credits_remaining }

Run it

Every call needs your API token in LOOOT_TOKEN; Sign in shows how to get one. Each run also needs a new idempotency key, so a retry never pays twice. With wait: 30 the answer comes back inline when the run ends within 30 seconds. Otherwise you get the running run back: poll GET /v1/runs/<runId>.

Example input with placeholder values:

curl -X POST "https://api.looot.ai/v1/runs" \
  -H "Authorization: Bearer $LOOOT_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"endpointId":"sumble-organizations","input":{"select":{},"organizations":[]},"wait":30}'

const response = await fetch("https://api.looot.ai/v1/runs", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.LOOOT_TOKEN}`,
    "Content-Type": "application/json",
    "Idempotency-Key": crypto.randomUUID(),
  },
  body: JSON.stringify({
    endpointId: "sumble-organizations",
    input: {
      select: {},
      organizations: [],
    },
    wait: 30,
  }),
});
const run = await response.json();
console.log(run.status, run.result);

import os
import uuid

import requests

response = requests.post(
    "https://api.looot.ai/v1/runs",
    headers={
        "Authorization": f"Bearer {os.environ['LOOOT_TOKEN']}",
        "Idempotency-Key": str(uuid.uuid4()),
    },
    json={
        "endpointId": "sumble-organizations",
        "input": {
            "select": {},
            "organizations": [],
        },
        "wait": 30,
    },
    timeout=90,
)
run = response.json()
print(run["status"], run.get("result"))

To let looot pick among every provider of this job instead, send job:organizations.get as endpointId; see the job page.