# Web reading with your AI agent

> Your agent reads public web pages and whole sites as Markdown, for your app or for its own work.

## What your agent can do

- Read one public page as clean Markdown.
- List the addresses of a site's pages without reading them.
- Read many pages of a site in the background, then page through the results.
- See which pages could not be read, and stop a running reading.

## Ask your agent

Paste a request like these in your AI once it is connected. It calls the tools in this order.

| You ask | Your agent calls |
|---|---|
| “Read example.com/pricing and summarise it.” | `search_scrape_page` |
| “Find the pages of example.com about webhooks.” | `search_map_site` |
| “Read the first 25 pages of example.com/docs.” | `search_map_site` → `search_start_crawl` → `search_get_crawl` |

## Tools and routes

Every tool is a call to the REST route next to it, with the same permissions, limits and idempotency. `tools/list` shows only the tools your connection can call.

| Tool | What it does | Scope | Same through the REST API |
|---|---|---|---|
| `search_scrape_page` | Read one public web page as clean Markdown. | `search:query` | `POST /v1/search/v2/scrape` |
| `search_map_site` | List the addresses of a site's pages, without reading them. | `search:query` | `POST /v1/search/v2/map` |
| `search_start_crawl` | Start a background reading of a site's pages, page after page. | `search:query` | `POST /v1/search/v2/crawl` |
| `search_get_crawl` | Read the status and the pages of a site reading. | `search:query` | `GET /v1/search/v2/crawl/{crawl_id}` |
| `search_get_crawl_errors` | List the pages a site reading could not read. | `search:query` | `GET /v1/search/v2/crawl/{crawl_id}/errors` |
| `search_cancel_crawl` | Stop a site reading that is still running. | `search:query` | `DELETE /v1/search/v2/crawl/{crawl_id}` |

## Limits, free tier and pricing

Read from the platform code each time this page is served.

| Limit | Value |
|---|---|
| Crawl pages (default limit) | **10** |
| Crawl pages (maximum per job) | **100** |
| Crawl depth (maximum) | **5** |
| Map links (maximum) | **1,000** |
| Page size (bytes) | **5 MiB** |
| Results kept (hours) | **24** |
| Concurrent crawl jobs per project | **2** |
| Pages per site per day (default) | **500** |
| Site reading requests per minute per key (default) | **60** |
| Page timeout (milliseconds, maximum) | **60,000** |
| Indexes per project (default) | **10** |
| Documents per index (default) | **100,000** |
| Documents per account (default) | **500,000** |
| Document size | **64 KiB** |
| Documents per batch | **1,000** |
| Queries per second per key (default) | **20** |

Usage prices, in US dollars, read from the price grid served by the platform each time this page is served. Paid from the prepaid balance.

| Item | Price | Unit |
|---|---|---|
| `page` | 0.741 USD | per 1,000 documents |
| `call` | 0.741 USD | per 1,000 requests |

Billing units: one page for scrape and crawl, one call for map, paid from the prepaid balance.

Your agent reads the current prices with `get_pricing` and the spending limits with `get_limits`.

## Good to know

- Galon obeys each site's robots.txt and reads public pages only; pages are not rendered with JavaScript.
- A site reading keeps its results 24 hours.

## Next

- [Full service documentation](/cloud/docs/services/search)
- [Connect your AI](/cloud/docs/ai-assistants)
- [All capabilities](/cloud/docs/agents)
- [API reference](/cloud/docs/api)
