--- title: Web data description: "Web data in the looot catalog as of 2026-09-28: 83 jobs served by 24 providers, with the job ids to run and links to the live catalog." sidebar: order: 4 --- {/* Generated by scripts/refresh-catalog.mjs from data/catalog-overview.json. Do not edit. */} As of 2026-09-28 (catalog revision 85280), **Web data** has 83 jobs across 16 platforms, served by 24 providers through 116 endpoints, 116 of them runnable now. The catalog changes every week; the live numbers are one call away: ```bash curl "https://api.looot.ai/v1/catalog/overview?category=web-data&depth=jobs" ``` Run any job below by its id: `endpointId: "job:"` on MCP `run` or `POST /v1/runs`, or `looot run job:`. See [Jobs](/concepts/jobs). ## Web data 36 jobs, 20 providers, 62 endpoints (62 runnable). Cheapest per call $0, per result $0.000145. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `web.scrape.structured` | Scrape a URL into structured JSON | 4 | $0.0012 | $0.0015 | | `news.search` | Search the news for a topic | 4 | $0.002 | n/a | | `jobs.search` | Search job listings | 4 | $0.002 | $0.000145 | | `web.scrape.markdown` | Scrape a web page into markdown | 4 | $0.0002 | n/a | | `web.article.extract` | Extract the article behind a URL | 3 | $0.001 | $0.001 | | `jobs.company` | List a company's open roles | 2 | $0.01 | n/a | | `web.answer` | Answer web | 2 | $0.005 | n/a | | `web.scrape.job.results` | Fetch the results of a scrape job | 2 | $0.0001 | $0.000333 | 28 more jobs: `GET /v1/catalog/overview?platform=web&depth=jobs`. ## Web monitors 5 jobs, 1 provider, 10 endpoints (10 runnable). Cheapest per call $0.015, per result n/a. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `monitors.runs` | Runs monitors | 1 | $0.015 | n/a | | `monitors.create` | Create monitors | 1 | $0.015 | n/a | | `monitors.get` | Get monitors | 1 | $0.015 | n/a | | `monitors.batch` | Batch monitors | 1 | $0.015 | n/a | | `monitors.trigger` | Trigger monitors | 1 | $0.015 | n/a | ## News 9 jobs, 1 provider, 9 endpoints (9 runnable). Cheapest per call $0.01, per result n/a. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `news.archive` | Archive news | 1 | $0.01 | n/a | | `news.count` | Count news | 1 | $0.01 | n/a | | `news.crypto` | Crypto news | 1 | $0.01 | n/a | | `news.crypto.count` | Count news crypto | 1 | $0.01 | n/a | | `news.market` | Market news | 1 | $0.01 | n/a | | `news.market.count` | Count news market | 1 | $0.01 | n/a | | `news.sources` | Sources news | 1 | $0.01 | n/a | | `news.websocket.fetch` | Fetch news websocket | 1 | $0.01 | n/a | 1 more job: `GET /v1/catalog/overview?platform=news&depth=jobs`. ## Browser tasks 7 jobs, 1 provider, 7 endpoints (7 runnable). Cheapest per call $0.05, per result $0.02. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `api.task.browser-use` | Browser use api task | 1 | n/a | $0.02 | | `api.task.claude-computer-use` | Claude computer use api task | 1 | $0.05 | n/a | | `api.task.cua` | Cua api task | 1 | $0.05 | n/a | | `api.task.gemini-computer-use` | Gemini computer use api task | 1 | $0.05 | n/a | | `api.task.grok-computer-use` | Grok computer use api task | 1 | $0.05 | n/a | | `api.task.hyper-agent` | Hyper agent api task | 1 | n/a | $0.02 | | `api.task.meta-computer-use` | Meta computer use api task | 1 | $0.05 | n/a | ## Research agents 4 jobs, 1 provider, 4 endpoints (4 runnable). Cheapest per call $0.012, per result n/a. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `agent.runs.create` | Create agent runs | 1 | $0.012 | n/a | | `agent.runs.events` | Events agent runs | 1 | $0.012 | n/a | | `agent.runs.get` | Get agent runs | 1 | $0.012 | n/a | | `agent.runs.stop` | Stop agent runs | 1 | $0.012 | n/a | ## Extraction 2 jobs, 4 providers, 4 endpoints (4 runnable). Cheapest per call $0.00044, per result $0.001. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `extract.get` | Get extract | 3 | $0.00044 | $0.001 | | `api.extract` | Extract api | 1 | $0.02 | n/a | ## Job postings 3 jobs, 1 provider, 3 endpoints (3 runnable). Cheapest per call $0, per result n/a. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `jobbase.collect` | Collect jobbase | 1 | $0.0196 | n/a | | `jobbase.search.es-dsl` | Es dsl jobbase search | 1 | $0 | n/a | | `jobbase.search.filter` | Filter jobbase search | 1 | $0 | n/a | ## Crawling 2 jobs, 2 providers, 2 endpoints (2 runnable). Cheapest per call n/a, per result $0.001. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `api.crawl` | Crawl api | 1 | n/a | $0.001 | | `crawl.get` | Get crawl | 1 | n/a | $0.0024 | ## The Guardian 2 jobs, 1 provider, 2 endpoints (2 runnable). Cheapest per call $0.036, per result n/a. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `api.guardian.articles` | Articles api guardian | 1 | $0.036 | n/a | | `api.guardian.authors.search` | Search api guardian authors | 1 | $0.0719 | n/a | ## Job postings (multi-source) 2 jobs, 1 provider, 2 endpoints (2 runnable). Cheapest per call $0, per result n/a. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `jobmultisource.collect` | Collect jobmultisource | 1 | $0.0196 | n/a | | `jobmultisource.search.es-dsl` | Es dsl jobmultisource search | 1 | $0 | n/a | ## The New York Times 2 jobs, 1 provider, 2 endpoints (2 runnable). Cheapest per call $0.0036, per result $0.00072. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `api.nytimes.articles` | Articles api nytimes | 1 | $0.0036 | n/a | | `api.nytimes.articles.search` | Search api nytimes articles | 1 | n/a | $0.00072 | ## Scraping 2 jobs, 1 provider, 2 endpoints (2 runnable). Cheapest per call $0.001, per result $0.001. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `api.scrape` | Scrape api | 1 | $0.001 | n/a | | `api.scrape.batch` | Batch api scrape | 1 | n/a | $0.001 | ## TechCrunch 2 jobs, 1 provider, 2 endpoints (2 runnable). Cheapest per call $0.0036, per result $0.00036. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `api.techcrunch.articles` | Articles api techcrunch | 1 | $0.0036 | n/a | | `api.techcrunch.articles.search` | Search api techcrunch articles | 1 | n/a | $0.00036 | ## The Verge 2 jobs, 1 provider, 2 endpoints (2 runnable). Cheapest per call $0.036, per result $0.0036. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `api.theverge.articles` | Articles api theverge | 1 | $0.036 | n/a | | `api.theverge.articles.search` | Search api theverge articles | 1 | n/a | $0.0036 | ## Web page parsing 2 jobs, 1 provider, 2 endpoints (2 runnable). Cheapest per call $0.0036, per result n/a. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `api.webparser.parse` | Parse api webparser | 1 | $0.0036 | n/a | | `api.webparser.render` | Render api webparser | 1 | $0.036 | n/a | ## Scraping actors 1 job, 1 provider, 1 endpoint (1 runnable). Cheapest per call $0.06, per result n/a. | Job id | What it does | Providers | Cheapest per call | Cheapest per result | | --- | --- | --- | --- | --- | | `actors.run` | Run actors | 1 | $0.06 | n/a | ## Find the right endpoint - Search by what you want done: MCP [`search`](/mcp-tools/search), `looot search ""`, or `GET /v1/catalog/search?q=`. - List one job's providers, cheapest first: `search` with `{"filters": {"capability": ""}, "prefer": "cheapest"}`. - Browse without an account: [looot.ai/public-catalog](https://looot.ai/public-catalog) or `GET https://api.looot.ai/v1/public-catalog?text=`.