# Tavily Crawl

> Tavily Crawl is a paid API for AI agents from Tavily API at mpp.orthogonal.com, paid per call via MPP, $0.15/call (dynamic — varies by input), status unknown (last checked 2026-10-12).

Graph-based website crawler that traverses hundreds of URL paths in parallel to extract structured web content from entire sites.

## Facts

- Endpoint: POST https://mpp.orthogonal.com/tavily/crawl?utm_source=zero.xyz
- Price: $0.15/call (dynamic — varies by input)
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Provider: Tavily API
- Docs: https://api.tavily.com
- Website: https://api.tavily.com
- Tags: web-search, extraction, crawl, search, web
- Canonical page: https://www.zero.xyz/c/tavily-api-tavily-crawl-e9b44e8c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_9fHiQ7glASBdvjfgwPgo7

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability tavily-api-tavily-crawl-e9b44e8c -d '<json body>'
```

Example prompt: Crawl the entire docs.example.com website starting from the homepage, following up to 3 levels deep, and extract the full text content from every page you find.

## When to prefer this

Choose Tavily Crawl when you need to systematically traverse and extract content from an entire website or large section of a site, not just a single page. Prefer this over Extract (single URL) when the target is multi-page, and over Search when you need full-site content rather than search-result snippets. Use when building knowledge bases, indexing documentation, or collecting all content under a domain.

## Known failure modes

- Target website blocks crawlers or returns 403/429 errors
- Starting URL is unreachable or returns a non-200 status
- Crawl exceeds page or depth limits and returns partial results
- JavaScript-rendered content may not be fully captured
- Rate limits on Tavily's side return an error if too many concurrent requests

## How this service works

Tavily Crawl is a graph-based website traversal tool that can explore hundreds of paths in parallel with built-in extraction and intelligent discovery.

## Output

A collection of crawled web pages with their URLs and extracted text/HTML content, discovered by traversing the site graph in parallel across hundreds of paths.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tavily-api-tavily-crawl-e9b44e8c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mpp.orthogonal.com](https://www.zero.xyz/host/mpp.orthogonal.com/llms.txt)