# Tavily Extract

> Extract clean, LLM-ready content (markdown or text) from up to 20 web pages in one call, optionally reranked to a query. Billed per successfully extracted URL - about 4 credits per URL (basic), failed URLs are refunded.

- **Provider**: tavily-extract
- **Model ID**: tavily/extract
- **Category**: web_search
- **Credits**: from 4 for the default configuration — varies by input, see Pricing
- **Pricing Type**: formula

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `urls` (array, **required**): Web page URLs to extract (1-20).
- `include_favicon` (boolean, optional): Add each page's favicon URL. (Default: `false`)
- `query` (string, optional): Optional intent to rerank the extracted chunks by relevance. With a query, raw_content holds the top chunks joined by [...].
- `chunks_per_source` (integer, optional): Chunks per URL when query is set (1-5, default 3). (Range: min: 1, max: 5)
- `format` (string, optional): Format of raw_content. (Default: `markdown`; Options: `markdown`, `text`)
- `extract_depth` (string, optional): advanced also extracts tables and embedded content and succeeds on more pages, at 2x price and higher latency. (Default: `basic`; Options: `basic`, `advanced`)
- `timeout` (number, optional): Per-request timeout in seconds (1-60). Default 10s for basic, 30s for advanced. (Range: min: 1, max: 60)
- `include_images` (boolean, optional): Add the image URLs found on each page. (Default: `false`)

## Example Request

```json
{
  "model": "tavily/extract",
  "input": {
    "format": "markdown",
    "urls": [
      "https://docs.tavily.com/documentation/api-credits"
    ],
    "extract_depth": "basic"
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "tavily-extract",
  "model": "tavily/extract",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null,
  "credits_used": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

When the job is `completed`, `result` holds the output URL(s) or data and `credits_used` the net credits charged. When it is `failed`, `error` and `error_code` say why and the charge is refunded.

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Pricing

- Formula: `3.72 * depth * max(1, min(min(20, urls), ok))` credits
  - `ok`: 99
  - `urls`: the `urls` input (default 1)
  - `depth`: the `extract_depth` input (default 1)

Default configuration: 4 credits.

These are list prices. The amount charged is rounded, and large charges are discounted progressively. `POST /predictions/estimate` with the same `model` and `input` returns the charge for that input without creating a job (an estimate when the price depends on the output).

## Output Type

json

## Tags

tavily, extract, web-scraping, rag, agent

## Documentation

https://docs.tavily.com/documentation/api-reference/endpoint/extract