Concepts

​

Overview

The Linkup /search endpoint allows you to discover and access relevant web content based on a natural language query. Once the content is retrieved, it can serve as factual grounding for Large Language Models (LLMs), helping them produce more accurate and informed responses.

​

Parameters

​

Query

Your query should be as specific as possible to improve the quality of the results. Consider providing additional context or constraints. For example:

​

Depth

You can choose between two search depths, depending on your performance and accuracy needs:

• standard: Returns results more quickly, suitable for low-latency scenarios. Costs €0.005 per call.
• deep: Continues to search iteratively if it doesn’t find sufficient information on the first attempt. This may take longer, but often yields more comprehensive results. Costs €0.05 per call.

When using deep, the system repeatedly evaluates whether it has found enough information. If not, it continues searching—potentially for tens of seconds—until it locates what it needs.

​

OutputType

The API supports several output formats to match different use cases:

• sourcedAnswer: Returns a natural language answer with source attributions.
• searchResults: Provides chunks of contextual data suitable for grounding in LLM prompts.
• structured: Produces a response following a specified JSON schema, ideal for structured data extraction.

​

Additional Parameters

• includeImages: Boolean parameter to include relevant images in search results
• fromDate: Filter results from a specific date (format: YYYY-MM-DD)
• toDate: Filter results until a specific date (format: YYYY-MM-DD)

​

Rate Limits

The API has a rate limit of 20 queries per second per account. If you need higher rate limits, please contact us to discuss custom plans.

​

Best Practices

1. Query Specificity

   • Be as specific as possible in your queries
   • Include relevant context (time periods, locations, industries)
   • Use natural language but be precise
   • Read our prompting guide to know more.

2. Depth Selection

   • Use standard for quick, general queries
   • Use deep for complex research or when accuracy is critical
   • Consider cost implications (€0.005 vs €0.05 per call)

3. Output Format

   • Choose sourcedAnswer for direct answers with citations
   • Use searchResults for LLM grounding
   • Select structured when you need specific data points returned in a json format. Read our structured output guide to know more.

4. Error Handling

   • The API returns standard HTTP status codes
   • No credit is deducted for failed requests
   • Common errors include:
     • 400: Bad Request (missing/invalid parameters)
     • 401: Unauthorized (invalid API key)
     • 429: Too Many Requests (rate limit or insufficient credit)