Search
Run a web search and get back structured results. Powered by Serper under the hood, with support for general, news, and finance topics.
POST
/v1/searchSearch the web and return structured results.
Request body
json
{
"query": "best open source LLM frameworks 2026",
"num": 10,
"topic": "general"
}Parameters
| Field | Type | Required | Description |
|---|---|---|---|
query | string | Yes | The search query string. |
num | integer | No | Number of results to return (1-100). Default: 10. |
topic | string | No | Search topic: "general", "news", or "finance". Adjusts ranking and source selection. Default: "general". |
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_...")
results = client.search("best open source LLM frameworks 2026")
for r in 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("best open source LLM frameworks 2026");
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": 10}'Note
Search costs 2 credits per 10 results requested. If you also pass
scrape: true, each fetched result adds 1 credit (or more if JS render or antibot fires). The news and finance topics may return fewer results depending on current coverage.