Extract

POST /search/v1/extract● Supported

Official Tavily docs ↗

Request body

querystring可选
User intent for reranking extracted content chunks. When provided, chunks are reranked based on relevance to this query.
urlsstring | array必填
URL to extract, or an array of up to 20 URLs. Per-URL failures are listed in `failed_results` of the response, which can come with HTTP 200.
chunks_per_sourceinteger可选
默认 3
Chunks are short content snippets (maximum 500 characters each) pulled directly from the source. Use `chunks_per_source` to define the maximum number of relevant chunks returned per source and to control the `raw_content` length. Chunks will appear in the `raw_content` field as: `<chunk 1> [...] <chunk 2> [...] <chunk 3>`. Available only when `query` is provided. Must be between 1 and 5.
extract_depthstring可选
默认 "basic"
The depth of the extraction process. `advanced` extraction retrieves more data, including tables and embedded content, with higher success but may increase latency.`basic` extraction costs 1 credit per 5 successful URL extractions, while `advanced` extraction costs 2 credits per 5 successful URL extractions.
取值 basicadvanced
include_imagesboolean可选
默认 false
Include a list of images extracted from the URLs in the response. Default is false.
include_faviconboolean可选
默认 false
Whether to include the favicon URL for each result.
formatstring可选
默认 "markdown"
The format of the extracted web page content. `markdown` returns content in markdown format. `text` returns plain text and may increase latency.
取值 markdowntext
timeoutnumber可选
默认 "None"
Maximum time in seconds to wait for the URL extraction before timing out. Must be between 1.0 and 60.0 seconds. If not specified, default timeouts are applied based on extract_depth: 10 seconds for basic extraction and 30 seconds for advanced extraction.
include_usageboolean可选
默认 false
Whether to include credit usage information in the response. `NOTE:`The value may be 0 if the total successful URL extractions has not yet reached 5 calls. See our [Credits & Pricing documentation](https://docs.tavily.com/documentation/api-credits) for details.

Returns

200

Errors follow the Tavily format — see error codes

Response

HTTP 200

Extraction completed. Check results and failed_results for each URL. HTTP 200 can have an empty results array when all valid URLs fail during extraction; output order is not guaranteed.

application/json

Name	Type	Description
results	array<object>	A list of extracted content from the provided URLs.
results[].url	string	The URL from which the content was extracted.
results[].raw_content	string	The full content extracted from the page. When `query` is provided, contains the top-ranked chunks joined by `[...]` separator.
results[].images	array<string>	This is only available if `include_images` is set to `true`. A list of image URLs extracted from the page.
results[].favicon	string	The favicon URL for the result.
failed_results	array<object>	A list of URLs that could not be processed.
failed_results[].url	string	The URL that failed to be processed.
failed_results[].error	string	An error message describing why the URL couldn't be processed.
response_time	number	Time in seconds it took to complete the request.
usage	object	Credit usage details for the request.
request_id	string	A unique request identifier you can share with customer support to help resolve issues with specific requests.