Data API / Tavily / Extract

Tavily Extract

Extract readable content from one URL or an array of URLs. Select text or Markdown with format. Inspect both results and failed_results: a failed URL can be reported in an otherwise successful HTTP response. Set include_usage to receive resource usage information; usage.credits is not a Felo charge.

Parameters

No path, query, or header parameters.

Request body

urlsRequired
The URL or URLs to extract content from. A single URL string and an array of URL strings are both accepted.
querystringOptional
User intent for reranking extracted content chunks.
chunks_per_sourceintegerOptional
Maximum number of relevant chunks returned per source. Available only when query is provided.
extract_depthstringOptional
Allowed values: basic · advanced
Depth of the extraction process.
include_imagesbooleanOptional
Include a list of images extracted from the URLs.
include_faviconbooleanOptional
Include the favicon URL for each result.
formatstringOptional
Allowed values: markdown · text
Format of the extracted web page content.
timeoutnumberOptional
Maximum time in seconds to wait for URL extraction. If omitted, default timeouts depend on extract_depth: 10 seconds for basic and 30 seconds for advanced.
include_usagebooleanOptional
Include resource usage information in the response. This is not Felo billing information.

Example request

curl -X POST "https://openapi.felo.ai/v1/beta/tavily/extract" \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "urls": {},
  "query": "<string>",
  "chunks_per_source": 0,
  "extract_depth": "<string>",
  "include_images": false,
  "include_favicon": false,
  "format": "<string>",
  "timeout": 0
}'

Response

Example response

{
  "results": [
    {
      "url": "https://example.com",
      "title": "Example Domain",
      "raw_content": "This domain is for use in documentation examples.",
      "images": []
    }
  ],
  "failed_results": [],
  "response_time": 0.5,
  "usage": {
    "credits": 1
  },
  "request_id": "example-extract-request"
}

Response fields

resultsobject[]Optional
urlstringOptional
URL of the extracted content.
titlestringOptional
Title of the extracted page.
raw_contentstringOptional
Extracted raw content from the URL.
imagesstring[]Optional
Images extracted from the URL when include_images is true.
faviconOptional
Favicon URL of the extracted content.
failed_resultsstring[]Optional
List of URLs that could not be processed.
response_timenumberOptional
Time in seconds it took to complete the request.
usageobjectOptional
creditsintegerOptional
Resource units consumed by this request, not USD or Felo credits.
request_idstringOptional
Unique request identifier.