Exa / Get page contents for URLs

Exa tool exa-contents on looot: input fields, $0.001 per result, output shape, and code to run it with curl, JavaScript or Python.

Fetches text, highlights or a summary for up to 100 URLs or Exa result ids in one call. Send urls or ids and pick text, highlights or summary; livecrawl and maxAgeHours control freshness.

Tool id: exa-contents
Provider: Exa
Job: Extract the article behind a URL (web.article.extract)
Price: $0.001 per result. A call that fails at the provider costs $0.

Inputs

Name	Type	Required	Description
`highlights`	unknown	no	Text snippets Exa’s LLM identifies as most relevant from each page. true for defaults, or an object to steer selection with your own query.
`ids`	array	no	Document ids obtained from a prior /search call, instead of urls.
`livecrawl`	string	no	Deprecated – use maxAgeHours instead (maxAgeHours: 0 replaces livecrawl: “always”). Kept only because the spec still accepts it; do not send alongside maxAgeHours.
`maxAgeHours`	integer	no	Max age of cached content in hours; 0 fetches fresh, -1 always uses cache. Deprecated livecrawl (never/always/fallback/preferred) is superseded by this – do not send both.
`summary`	unknown	no	LLM-generated summary of the webpage, optionally guided by a query or returned structured against a JSON schema.
`text`	unknown	no	Full page text for each result. true for defaults with default settings, or an object for advanced control.
`urls`	array	yes	URLs to crawl.

Output

Shape of the run’s result, checked against 3 real answers:

{ results: { id, url, text, image, title, author, entities: { id, type, version, properties: { ... } }[] }[], statuses: { id, error: { tag, httpStatusCode }, source, status }[], requestId, searchTime, costDollars: { total, contents: { text } } }

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":"exa-contents","input":{"urls":["https://arxiv.org/pdf/2307.06435"]},"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: "exa-contents",
    input: {
      urls: ["https://arxiv.org/pdf/2307.06435"],
    },
    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": "exa-contents",
        "input": {
            "urls": ["https://arxiv.org/pdf/2307.06435"],
        },
        "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:web.article.extract as endpointId; see the job page.

Exa / Get page contents for URLs

Inputs

Output

Run it