Search

Run a web search and get structured results, with optional page content. Use country, language, domain filters, and freshness hints to narrow discovery.

POST/v1/search

Search the web and return structured results.

Request body

json

{
  "query": "best open source LLM frameworks 2026",
  "num_results": 5,
  "scrape": false
}

Parameters

Field	Type	Required	Description
`query`	`string`	Yes	The search query string.
`num_results`	`integer`	No	Number of results to return (1–10). Default: 5. Fewer may be available.
`scrape`	`boolean`	No	Whether to fetch result pages and include their content. Default: true.

Note

Unknown fields return 400. Use num_results, not num. Search does not accept topic; that option belongs to Research. With scraping enabled, inspect each result's error before using its content.

Optional formats accepts markdown, text, llm, or json (default: markdown). country and lang localize results. include_domains, exclude_domains, and include_url_prefixes each accept up to 20 strings. page is 1–100 (default: 1); location and autocorrect are optional provider hints. freshness accepts hour, day, week, month, or year, or use published_after and published_before as YYYY-MM-DD dates. Do not combine freshness with explicit dates. These hints do not verify publication dates. Use no_cache: true for a fresh request or max_cache_age in seconds.

Response

json

{
  "results": [
    {
      "title": "Top Open Source LLM Frameworks in 2026",
      "url": "https://example.com/llm-frameworks",
      "snippet": "A comprehensive comparison of the leading open source frameworks for building LLM applications...",
      "position": 1
    },
    {
      "title": "LLM Framework Benchmark Results",
      "url": "https://example.com/benchmarks",
      "snippet": "We tested 12 frameworks across latency, memory usage, and developer experience...",
      "position": 2
    }
  ]
}

Result object

Field	Type	Description
`title`	`string`	Page title from the search result.
`url`	`string`	URL of the search result.
`snippet`	`string`	Text excerpt from the page relevant to the query.
`position`	`integer`	1-based ranking position in the search results.

SDK examples

Python

python

from webclaw import Webclaw

client = Webclaw(api_key="wc_...")

response = client.search("best open source LLM frameworks 2026", num_results=5)
for r in response["results"]:
    print(f"{r['position']}. {r['title']} — {r['url']}")

TypeScript

typescript

import { Webclaw } from "@webclaw/sdk";

const client = new Webclaw({ apiKey: "wc_..." });

const { results } = await client.search({
  query: "best open source LLM frameworks 2026",
  num_results: 5,
  scrape: false,
});
results.forEach((r) => console.log(`${r.position}. ${r.title}`));

cURL

bash

curl -X POST https://api.webclaw.io/v1/search \
  -H "Authorization: Bearer wc_..." \
  -H "Content-Type: application/json" \
  -d '{"query": "best open source LLM frameworks 2026", "num_results": 5}'