# Tavily Extract API (https://www.socialcrawl.dev/platforms/tavily/extract)

> Pulls clean, AI-ready text out of one or more URLs via Tavily's extractor. Pass a single URL or a comma-separated list (max 20). Returns extracted content per URL alongside any URLs that failed extraction. Use `extract_depth=advanced` for harder pages (paywalls, JS-heavy SPAs).

TL;DR: `GET /v1/tavily/extract` costs 1 credit per call and returns SocialCrawl's unified JSON schema. Single x-api-key auth, 100 free credits on signup.

## Parameters

| Parameter | Required | Description |
| --- | --- | --- |
| `urls` | yes | Comma-separated list of URLs to extract (max 20). |
| `extract_depth` | no | Extraction strategy. `basic` is the default and faster; `advanced` handles harder pages but takes longer. (basic \| advanced) |
| `format` | no | Output format for the extracted content. `markdown` (default) preserves structure; `text` is plain. (markdown \| text) |
| `include_images` | no | Include images extracted from each URL. |
| `include_favicon` | no | Include the favicon URL for each page. |
| `timeout` | no | Per-URL timeout in seconds (1–60). |

## Code example

```bash
curl "https://www.socialcrawl.dev/v1/tavily/extract?urls=https%3A%2F%2Fen.wikipedia.org%2Fwiki%2FLionel_Messi" \
  -H "x-api-key: sc_YOUR_API_KEY"
```

## FAQ

### How do I extract content from a URL with the Tavily API?

Send a GET request to /v1/tavily/extract with one or more URLs in the urls parameter and your SocialCrawl x-api-key. You get back the clean readable content of each page, stripped of navigation and boilerplate, ready for RAG or summarisation.

### Can I extract several URLs in one request?

Yes. Pass multiple URLs and Tavily extracts each in the same call, returning a result per URL plus any that failed. This is the efficient pattern when you already have a list of links from a Tavily search or your own pipeline.

### What options control how content is extracted?

extract_depth (basic or advanced; advanced parses tables and embedded content more thoroughly) and format (the shape of the returned content, e.g. markdown or text). Set advanced depth when pages are dense or structured.

### When should I use extract instead of search?

Use extract when you already have the URLs and just need their content; use search when you need to find pages for a query first. A common flow is search to discover links, then extract to read them. Both run on the same SocialCrawl key.

### How much does the Tavily Extract API cost?

Each extract call costs 1 credit on the standard tier. New accounts get 100 free credits with no credit card required, enough to extract content from many URLs while you wire up your ingestion pipeline before you pay.

See the full Tavily API: https://www.socialcrawl.dev/platforms/tavily

## Pricing

- Standard endpoints: 1 credit per call
- Advanced endpoints: 5 credits per call
- Premium endpoints: 10 credits per call
- 100 free credits on signup, no credit card required. Cached responses cost 0 credits. Credit packs never expire.
- Full pricing: https://www.socialcrawl.dev/pricing

## Explore with AI

Questions this API answers, phrased for an AI assistant:

- How to extract clean URL content with the Tavily API on SocialCrawl
- Can the SocialCrawl Tavily extract endpoint read several URLs at once?