# Tavily Extract

> Tavily Extract is a paid API for AI agents from Tavily at tavily.mpp.paywithlocus.com, paid per call via MPP, $0.11+ (scales with URL count) (dynamic), status unknown (last checked 2026-10-10).

Extracts and returns the full text content from one or more URLs using Tavily's AI-optimized extraction engine

## Facts

- Endpoint: POST https://tavily.mpp.paywithlocus.com/tavily/extract?utm_source=zero.xyz
- Price: $0.11+ (scales with URL count) (dynamic)
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Provider: Tavily
- Docs: https://docs.tavily.com
- Website: https://tavily.com
- Tags: ai-search, web-search, extraction, crawling, search, web
- Canonical page: https://www.zero.xyz/c/tavily-extract-94ed55a2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap__OhlXxRbpQn1j-50W7CWe

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-extract-94ed55a2 -d '<json body>'
```

Example prompt: Can you extract the full text content from these two URLs for me: https://example.com/article1 and https://example.com/article2 — use advanced extraction depth to make sure you get everything?

## When to prefer this

Use Tavily Extract when you need to retrieve and parse the raw text content of specific known URLs (up to 20 at a time), especially when you need AI-optimized extraction that handles dynamic content better than naive HTTP fetches. Prefer this over Tavily Search when you already have the URLs and just need their content, and over Tavily Crawl when you don't need to follow links across a whole site.

## Known failure modes

- URL is unreachable or returns a non-200 status — extraction fails for that URL
- Paywall or bot-detection blocks content retrieval — partial or empty content returned
- Invalid URL format provided — validation error
- More than 20 URLs submitted — request rejected
- Timeout on slow-loading pages — partial content or error returned

## How this service works

Extract clean content from one or more URLs. Returns parsed text optimized for LLM consumption.

## Output

Returns the extracted text content from the provided URLs, including the main body text, structured content, and metadata parsed from each page, ready for downstream processing or analysis.

## Example request

```json
{
 "urls": "https://example.com",
 "extract_depth": "basic"
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "urls"
 ],
 "properties": {
  "urls": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "URLs to extract content from (max 20)"
  },
  "extract_depth": {
   "type": "string",
   "description": "Extraction depth: 'basic' (default) or 'advanced'"
  }
 },
 "additionalProperties": true
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tavily-extract-94ed55a2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from tavily.mpp.paywithlocus.com](https://www.zero.xyz/host/tavily.mpp.paywithlocus.com/llms.txt)