Skip to main content
The search_depth parameter controls the tradeoff between latency, cost, and content richness. Pick the right depth for each query instead of over-fetching.

When to use each search depth

Lite — short snippets for simple questions

Use lite when a one-sentence snippet answers the question on its own, or you need to scan many results without reading full pages. Good for:
  • Quick factual questions (“when was X founded”, “what’s the latest release of Y”)
  • High-volume monitoring where you only need to detect new mentions
  • Scanning and filtering before deciding what’s worth going deeper on

Standard — rich content for AI agents

Use standard when you need enough content to answer questions or feed an LLM, without the latency of scraping every page in real time. Returns rich content optimized for AI consumption. It’s the default depth when a request omits search_depth. Good for:
  • RAG pipelines and chatbot grounding
  • Real-time agent workflows where latency matters
  • Q&A systems that need context beyond snippets
  • Any AI application that needs content, not just links

Full page content

Add full_content: true when you need complete source material from every result, on top of either depth. Each page is scraped in real time and its full content returned alongside the usual title, URL, and description. Good for:
  • Research and due diligence requiring complete source text
  • Building comprehensive knowledge bases
  • Content analysis where snippets are insufficient
  • Legal or compliance workflows needing full page archives

Cost optimization

Start lite, go deeper when needed

The most cost-effective pattern: search with lite first, then use Extract on the specific URLs that matter.

Choose depth by query type

Not every query needs the same depth. Match depth to intent:

Combining depth with other features

Depth + domain filtering

Narrow your search to trusted sources before extracting content:

Depth + time filtering

Combine depth with recency filters for targeted research:

Focus Modes

Company

Use focus: "company" to discover businesses or look up a known company. You can search by product, market, geography, revenue and more in your query to find relevant companies, for example: “B2B payment infrastructure companies in Europe.” Returned data: optional company records in entities, with fields such as name, headquarters, workforce_total, financials and web_traffic. Content: at standard depth, content holds a short company profile (about 2,000 characters) in markdown. At lite it’s empty. Add full_content: true for the complete profile, including financials, funding rounds and workforce breakdown. Company returns up to 25 results per call.

Creators

Use focus: "creators" to find Instagram and TikTok creators. You can specify platform, topic and desired audience size in plain language, for example: “TikTok vegetarian-recipe creators with more than 10,000 followers.” Returned data: optional creator records in entities, with fields such as platform, username, display_name, followers_count, posts_count and is_verified. Content: title is the display name and @handle, url is the profile, and description is the bio, which can be empty. content is empty unless you set full_content: true, which returns a markdown profile. Creators follows max_results with no fixed cap. Platform targeting: domain filters apply after retrieval and can reduce the count. To target one platform, name it in the query, for example “Instagram fitness creators”, rather than relying on include_domains.

Next steps

Quickstart

Full Search documentation with all features and focus modes

API Reference

Complete parameter documentation and response schemas