How do I get Top Stories (News Box) data from Scavio?

Send a search request with the appropriate platform (google) and Scavio returns top stories (news box) data in the response. See the example above for the exact field path.

Is Top Stories (News Box) data available in real time?

Yes. Scavio fetches top stories (news box) data in real time on each request. There is no caching layer and no stale data.

How much does Top Stories (News Box) data cost?

Top Stories (News Box) data is returned as part of the standard search response. Each request costs 1 credit. Free tier includes 500 credits/month.

Top Stories (News Box) API: Fetch Top Stories (News Box) Data via Scavio

What is Top Stories (News Box)?

The Top Stories box is the news carousel Google inserts for queries with a freshness signal, such as breaking events, public companies, or trending topics. Scavio returns each story with the headline, publisher name, publisher domain, ISO-formatted published timestamp, a thumbnail, and the article URL. We also flag whether a story is part of a 'Full Coverage' cluster, and when present, we return the cluster's topic label so you can group related articles. For news monitoring, PR, and investor workflows, this gives you Google's own editorial view of what is most relevant right now, which often differs from what specific publisher RSS feeds would surface.

Example Response

JSON

{
  "news_box": [
    {
      "position": 1,
      "title": "Anthropic Unveils Claude Opus 4.6 With Longer Context Window",
      "publisher": "TechCrunch",
      "publisher_domain": "techcrunch.com",
      "published": "2 hours ago",
      "published_iso": "2026-04-16T12:10:00Z",
      "thumbnail": "https://serpapi.scavio.dev/news/claude-opus-46.jpg",
      "link": "https://techcrunch.com/2026/04/16/anthropic-opus-46",
      "cluster": "Claude Opus 4.6 launch"
    },
    {
      "position": 2,
      "title": "Claude Opus 4.6 benchmarks beat GPT-6 on agentic tasks",
      "publisher": "The Verge",
      "publisher_domain": "theverge.com",
      "published": "1 hour ago",
      "published_iso": "2026-04-16T13:05:00Z",
      "thumbnail": "https://serpapi.scavio.dev/news/opus-benchmarks.jpg",
      "link": "https://theverge.com/2026/4/16/opus-46-benchmarks",
      "cluster": "Claude Opus 4.6 launch"
    }
  ]
}

Use Cases

Real-time brand and executive mention monitoring
Financial and earnings news tracking for public tickers
News aggregator apps and topic digests
PR share-of-voice reports against competitors
Grounding LLM answers with freshly published sources

Why Top Stories (News Box) Matters

News freshness is a first-class ranking factor for many queries, and Google's Top Stories placement drives massive bursts of referral traffic. Scavio normalizes publisher names and clusters related coverage so PR teams can measure true story reach rather than raw article counts. AI teams benefit from getting high-recency sources with timestamps they can trust, which is essential for any agent answering questions about ongoing events.

LangChain Example

Drop top stories (news box) data into your LangChain agent in a few lines:

Python

from langchain_scavio import ScavioSERPTool

tool = ScavioSERPTool(api_key="your_scavio_api_key", extract="news_box")

data = tool.invoke({"query": "claude opus 4.6"})

clusters = {}
for story in data["news_box"]:
    clusters.setdefault(story["cluster"], []).append(story["publisher"])

for cluster, publishers in clusters.items():
    print(f"{cluster}: covered by {len(publishers)} publishers")

Top Stories (News Box)