面向AI智能体的网页搜索API
为LLM工具调用打造的实时网页搜索端点。可预测的JSON输出、国家与日期过滤,按调用计费 — 可接入OpenAI函数调用、Claude工具使用或任何智能体框架。
API Integration Guide
Learn how to integrate this API into your applications with code examples and detailed documentation.
/api/search/webBase URL
https://www.apipick.comFull Endpoint
https://www.apipick.com/api/search/webqueryNatural-language search query
max_num_results1–5, default 5
relevance_threshold0.0–1.0 quality filter
country_codeISO country code (e.g. US, GB)
start_dateISO date YYYY-MM-DD
end_dateISO date YYYY-MM-DD
cURL Request
curl -X POST "https://www.apipick.com/api/search/web" \
-H "Content-Type: application/json" \
-H "x-api-key: YOUR_API_KEY" \
-d '{
"query": "latest developments in quantum computing",
"max_num_results": 5,
"country_code": "US",
"start_date": "2026-01-01"
}'YOUR_API_KEY with your actual API keyJSON Response
{
"query": "latest developments in quantum computing",
"results": [
{
"title": "Example result",
"url": "https://example.com/article",
"snippet": "Short excerpt of the page content…",
"source_type": "web",
"published_at": "2026-04-15",
"score": 0.92
}
],
"result_count": 1,
"credits_used": 15,
"remaining_credits": 99
}✓Best Practices
- • Always include x-api-key header
- • Always handle errors gracefully
- • Validate input data before sending
- • Use HTTPS for secure communication
- • Cache responses when appropriate
ℹResponse Headers
- • Content-Type: application/json
- • x-api-key: Required for authentication
- • Status codes: 200 (success), 400 (error), 401 (unauthorized)
- • No rate limiting applied
Rate Limits
Request Rate
60req / min
Per API key, per endpoint. Sliding 60-second window.
Concurrency
3concurrent
Max simultaneous in-flight requests per API key.
Response Headers
429 Too Many Requests
HTTP/1.1 429 Too Many Requests
Retry-After: 12
X-RateLimit-Limit: 60
X-RateLimit-Remaining: 0
X-RateLimit-Reset: 12
{
"error": "rate_limit_exceeded",
"message": "Rate limit exceeded: 60 requests/minute per API key. Retry after 12s.",
"retry_after": 12
}常见问题
与Google或Bing搜索API有何不同?
响应已为LLM消费预先成型:短摘要(无样板)、结构化JSON、相关性评分。无需在喂给模型前再做单独的抓取与清洗步骤。
结果如何排序?
结果通过语义嵌入而非关键词匹配排序,因此即使措辞不同,相似含义也会靠近。也可传入 relevance_threshold(0.0–1.0)来过滤低质量结果。
可以限制特定国家或日期范围吗?
可以。传入 country_code(ISO 3166-1 alpha-2,如 US、JP)和/或 start_date / end_date,格式为 YYYY-MM-DD。
失败的调用如何计费?
如果搜索失败(5xx或无效查询),不扣除积分。仅对成功的2xx响应计费。
有OpenAI函数调用的工具Schema吗?
有。GET /api/search/web/tool-schema 返回可直接粘贴的OpenAI函数和Claude工具使用定义。