Tavily Extract
从已知URL抽取正文,支持相关问题、分块数量、深度、图片和输出格式。兼容单个URL或URL数组。部分网页可能抽取失败,需检查failed_results;按实际用量结算。通过 Tavily Extract API 同步返回抽取结果:results 包含成功页面的 URL 和 raw_content,正文格式可选 Markdown 或纯文本;提供 query 时,raw_content 返回相关片段而非完整抽取内容。可按选项附带图片链接、站点图标和估计的发布时间或更新时间。failed_results 列出失败 URL 及原因;即使请求成功,results 也可能为空。
Pricing
The charge per call is (max(6 × Actual extraction usage, 0)) AE credits. All applicable conditions are combined to calculate the total.
Actual extraction usage depends on the number of successfully extracted pages and the extraction depth. The default depth is basic; advanced consumes more usage. Failed URL extractions are not charged. A call may also have no charge when the accumulated number of successful extractions has not yet reached a billing batch.
Parameters
Optional parameters use the platform defaults when omitted.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
urls | string | array | Yes | 待抽取网页;兼容单个URL字符串或URL数组。 | — |
query | string | No | 搜索问题或关键词。 | — |
format | enum (markdown | text) | No | 网页内容格式,markdown或text。 | markdown |
timeout | number | No | 上游单次执行的最长等待秒数。 | — |
extract_depth | enum (basic | advanced) | No | 正文抽取深度,advanced消耗更多积分。 | basic |
include_images | boolean | No | 是否返回图片。 | false |
include_favicon | boolean | No | 是否返回站点图标。 | false |
chunks_per_source | integer | No | 每个来源最多返回的相关片段数;不是严格的字符长度上限。 | 3 |
include_published_date | boolean | No | 是否返回发布时间信息。 | false |
Invocation example
Copy the request and explore its response example.
/agent-api/v1/tool/executeX-Api-Keycurl --request POST \
--url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_tavily_extract' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"chunks_per_source": 1,
"include_published_date": true,
"query": "TaskGroup exception cancellation handling",
"urls": "https://docs.python.org/3/library/asyncio-task.html"
}
}'{
"failed_results": [],
"response_time": 0.07,
"results": [
{
"images": [],
"published_date": "Sun, 18 Oct 2026 17:00:00 GMT",
"raw_content": "Task groups are careful not to mix up the internal cancellation used to “wake up” their `__aexit__()` with cancellation requests for the task in which they are running made by other parties. In particular, when one task group is syntactically nested in ano",
"title": "Coroutines and tasks — Python 3.15.2 documentation",
"url": "https://docs.python.org/3/library/asyncio-task.html"
}
],
"usage": {}
}This example shows part of the response. Copied content is valid JSON.
Guides using this tool
See how this tool fits into real workflows





