> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nemu.cc/llms.txt
> Use this file to discover all available pages before exploring further.

# Web research

> Search, read pages, and dispatch a researcher that comes back with sources

Turn **Web** on in the composer's tools menu and the assistant can search and
read pages. Turn **Analysis** on as well and it can run deep research.

New chats have web search on by default.

## What it can do

**Search** returns six results, or ten when analysis is on.

**Read a page** pulls the readable text, up to about 20,000 characters. If a
page comes back nearly empty the assistant is told it was blocked or needs
JavaScript, rather than silently reporting nothing.

**Find on a page** pulls the passages matching a question out of a long
document, which is how it handles a large PDF without reading all of it.

**Research** hands the whole question to a [subagent](/chat/subagents) that
searches, reads and returns an answer with its sources. Shallow research spends
about twelve steps, deep about twice that.

## Sources

Any answer built from the web carries a sources button. Opening it lists every
page referenced, with its site, title, description and preview image.

## Daily limits

|               | Free | Starter |   Pro |    Max | Enterprise |
| ------------- | ---: | ------: | ----: | -----: | ---------: |
| Searches      |   25 |   1,000 | 5,000 | 15,000 | 10,000,000 |
| Deep searches |    3 |     200 | 1,000 |  3,000 | 10,000,000 |
| Page reads    |   25 |   1,000 | 5,000 | 15,000 | 10,000,000 |

On paid plans these also draw from [credits](/computer/credits) at €0.006 a
search, €0.003 a page read and €0.05 a deep search.

Results are cached for a day, so asking the same thing twice does not cost
twice.

When a limit is reached the assistant is told to stop searching and report what
it already found, rather than failing mid answer.