Tavily Crawl
从起始URL探索并抽取多页内容,支持相关指令、分块、深度、数量、域名及路径筛选。通过Tavily Crawl API同步返回各页面的URL和抽取正文,正文可选择Markdown或纯文本格式;不是仅返回链接的站点映射。探索范围受深度、广度、页面数量和筛选条件限制。费用包含发现链接和正文抽取的实际用量。
Pricing
The charge per call is (max(6 × Actual crawl usage, 0)) AE credits. All applicable conditions are combined to calculate the total.
Charges include both link discovery and content extraction. Usage depends on the number of pages successfully discovered, the number of URLs successfully extracted, the extraction depth, and whether natural-language instructions are provided. Advanced extraction and natural-language instructions increase usage for their respective operations. Crawl depth, breadth, page limits, and filters affect the processing scope; the requested page limit is not the actual number of pages returned. Zero actual usage incurs no charge.
Parameters
Optional parameters use the platform defaults when omitted.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
url | string | Yes | 起始网页URL。 | — |
limit | integer | No | 最多处理或返回的页面数量;会影响预占及最终费用。 | 50 |
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。 | 150 |
max_depth | integer | No | 从起始URL向外探索的层数。 | 1 |
max_breadth | integer | No | 每个页面最多继续访问的链接数。 | 20 |
instructions | string | No | 描述希望寻找的内容或页面类型;填写后可能增加供应商用量。 | — |
select_paths | array | No | 仅选择匹配这些正则表达式的路径。 | — |
exclude_paths | array | No | 排除匹配这些正则表达式的路径。 | — |
extract_depth | enum (basic | advanced) | No | 正文抽取深度,advanced消耗更多积分。 | basic |
allow_external | boolean | No | 是否允许结果含站外链接。 | true |
include_images | boolean | No | 是否返回图片。 | false |
select_domains | array | No | 仅选择匹配这些表达式的域名。 | — |
exclude_domains | array | No | 排除的域名列表。 | — |
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 |
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_crawl' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"chunks_per_source": 1,
"instructions": "Extract TaskGroup exception cancellation handling",
"limit": 1,
"max_breadth": 1,
"max_depth": 1,
"url": "https://docs.python.org/3/library/asyncio-task.html"
}
}'{
"base_url": "https://docs.python.org/3/library/asyncio-task.html",
"response_time": 1.82,
"results": [
{
"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",
"url": "https://docs.python.org/3/library/asyncio-task.html"
}
],
"usage": {}
}This example shows part of the response. Copied content is valid JSON.





