Exa: Contents - Deepline

Scrape web pages by URL: get the text content, summaries, and highlights of company websites, articles, and profile pages.

Tool ID: exa_contents

Run this action

Use the TypeScript SDK for one call. Use ctx.tools.execute(...) inside a Play for durable calls, scheduled calls, or CSV processing.

import { Deepline } from 'deepline';

const deepline = await Deepline.connect();
const result = await deepline.tools.execute(
  'exa_contents',
  {
    "urls": [
      "https://example.com"
    ],
    "ids": [
      "id_123"
    ],
    "text": true
  },
);

console.log(result.toolResponse.raw);

CLI

deepline tools execute exa_contents --input '{
  "urls": [
    "https://example.com"
  ],
  "ids": [
    "id_123"
  ],
  "text": true
}' --json

Example response

The SDK returns this shape at result.toolResponse.raw. The example values illustrate the response.

{
  "data": {
    "requestId": "request_123",
    "results": [
      {
        "id": "id_123",
        "url": "https://example.com",
        "title": "VP of Engineering"
      }
    ],
    "context": "example"
  }
}

Use deepline describe exa_contents --json for the latest machine-readable contract.

Input reference

Exa contents input.

Name	Type	Required	Default	Details
`payload.urls`	`array`	No	—	URLs to fetch contents for (alias of ids).
`payload.ids`	`array`	No	—	Document IDs (or URLs) to fetch contents for.
`payload.text`	`boolean \| object`	No	—	—
`payload.highlights`	`boolean \| object`	No	—	—
`payload.summary`	`object`	No	—	LLM-generated summary of each page (structured output supported).
`payload.livecrawl`	`"never" \| "fallback" \| "preferred" \| "always"`	No	—	Live crawl behavior (deprecated in Exa docs. prefer maxAgeHours). Allowed: `never`, `fallback`, `preferred`, `always`.
`payload.livecrawlTimeout`	`number`	No	—	Live crawl timeout in milliseconds.
`payload.maxAgeHours`	`number`	No	—	Max age (hours) for cached content before live crawl.
`payload.subpages`	`number`	No	—	Number of subpages to crawl from each result.
`payload.subpageTarget`	`string \| array`	No	—	Subpage keyword(s) to target.
`payload.extras`	`object`	No	—	Extra content options.
`payload.context`	`boolean \| object`	No	—	Return a combined context string. When true, combines all result contents into one string (10,000+ chars recommended).

Output reference

Exa contents result.

Name	Type	Required	Default	Details
`result.data`	`object`	Yes	—	Provider response payload.
`result.data.requestId`	`string`	No	—	—
`result.data.results`	`array`	No	—	—
`result.data.results[].id`	`string`	No	—	—
`result.data.results[].url`	`string`	No	—	—
`result.data.results[].title`	`string`	No	—	—
`result.data.results[].text`	`string`	No	—	—
`result.data.results[].publishedDate`	`string`	No	—	—
`result.data.results[].author`	`string \| unknown`	No	—	—
`result.data.results[].score`	`number`	No	—	—
`result.data.results[].highlights`	`array`	No	—	—
`result.data.results[].highlightScores`	`array`	No	—	—
`result.data.results[].summary`	`string \| record`	No	—	—
`result.data.results[].entities`	`array`	No	—	—
`result.data.results[].entities[].id`	`string`	No	—	—
`result.data.results[].entities[].type`	`"company" \| "person"`	No	—	Allowed: `company`, `person`.
`result.data.results[].entities[].version`	`number`	No	—	—
`result.data.results[].entities[].properties`	`record`	No	—	—
`result.data.results[].extras`	`record`	No	—	—
`result.data.results[].subpages`	`array`	No	—	—
`result.data.results[].subpages[].id`	`string`	No	—	—
`result.data.results[].subpages[].url`	`string`	No	—	—
`result.data.results[].subpages[].title`	`string`	No	—	—
`result.data.results[].subpages[].text`	`string`	No	—	—
`result.data.results[].subpages[].publishedDate`	`string`	No	—	—
`result.data.results[].subpages[].author`	`string \| unknown`	No	—	—
`result.data.results[].subpages[].score`	`number`	No	—	—
`result.data.results[].subpages[].highlights`	`array`	No	—	—
`result.data.results[].subpages[].highlightScores`	`array`	No	—	—
`result.data.results[].subpages[].summary`	`string \| record`	No	—	—
`result.data.results[].subpages[].entities`	`array`	No	—	—
`result.data.results[].subpages[].entities[].id`	`string`	No	—	—
`result.data.results[].subpages[].entities[].type`	`"company" \| "person"`	No	—	Allowed: `company`, `person`.
`result.data.results[].subpages[].entities[].version`	`number`	No	—	—
`result.data.results[].subpages[].entities[].properties`	`record`	No	—	—
`result.data.results[].subpages[].extras`	`record`	No	—	—
`result.data.context`	`string`	No	—	—
`result.meta`	`record`	No	—	Additional response metadata (status, paging).

Deepline cost

Pricing model: per_result (per result).
Estimated Deepline credits: 0.02 per pricing unit.

​Run this action

​CLI

​Example response

​Input reference

​Output reference

​Deepline cost

​Related documentation

Run this action

CLI

Example response

Input reference

Output reference

Deepline cost

Related documentation