# Web search

Use Exa search to find public URLs for a question, and Exa contents to retrieve the text of a known page. A useful research task combines both: discover relevant sources, read the strongest ones, and produce a comparison whose claims link back to those sources.

## Web search

- ### Search input

query is required. limit defaults to 8; the agent catalog accepts 1–20 results.

- ### Page retrieval

Provide one public URL. The current Exa adapter requests page text and returns url, content and provider.

- ### Task example

Research three alternatives to a named product. Return a table of feature differences, supporting page URLs and unresolved questions.

## Tool usage

Tool charges use the same configured cost basis and 2× multiplier as billing. Model and runtime charges are separate.

The charge follows the operation and billable units shown here.

- ### exa.search

$0.01 per run.

- ### exa.contents

$0.002 per page.

## Example tasks

### Put it to work

Choose an example and adapt its input and intended result to your task.

- ### Research a topic

Find the official documentation for browser-based AI agents. Compare three approaches and cite the pages supporting each claim.

- ### Find recent sources

Find recent primary-source announcements about agent evaluation. Include publication dates and explain why each source matters.

## Common questions

### How many search results can I request?

### Can I request Markdown, JSON and text page output?

### When should I use Web search instead of Browser use?

### What should I include in a search request?

### Are search snippets enough to support an answer?

### Can I search and read a page in the same operation?

### How much is one search followed by reading ten pages?

### Can I filter by date or domain through this adapter?

### What if I already have the source URLs?

### How much does web search cost?