AMAZINGINDEX.COM 让生活多一点 Amazing
56.6
VOL. 2026.10
2026.10.19
← 返回 2026.10.19 日报
日报快照 · Daily Snapshot
NO. 011

DeepSeek 推出搜索抓取 API,$0.75/千次

#ARTICLE HackerNews 2026.10.19
推荐指数 61.0 NO. 011 · 2026.10.19
发布2026/10/18Score477Comments233

DeepSeek 上线 Search API 和 Fetch API,提供实时网页搜索与内容抓取能力,定价 $0.75 每千次成功请求。对做 RAG 和 Agent 的团队来说,这是比自建爬虫或接 SerpAPI 更便宜的官方方案,尤其适合需要中文搜索覆盖的场景。

做 Agent 的团队之前接实时搜索主要靠 SerpAPI 或自建 Bing/Google 代理,SerpAPI 定价约 $0.50-2/千次但稳定性参差,自建则面临反爬和合规成本。DeepSeek 这次把搜索和抓取打包成原生 API,且用自家搜索引擎而非代理第三方,意味着中文搜索质量可能更可控。

值得关注的是它把 fetch 和 search 拆成两个端点,说明设计上鼓励先搜后抓的流水线模式,而不是直接给大段摘要。如果你的 Agent 需要频繁查最新资料,现在可以对比测试它和 Firecrawl、Jina AI Reader 的延迟和召回率,成本上 DeepSeek 有明显优势。

负面 154 条评论

核心争论:AI爬虫绕过反bot机制是否道德,服务方与网站所有者的利益冲突

Doohickey-d

How well does this (and similar services) deal with anti-bot protection? What happens if I attempt to retrieve a page protected by the cloudflare checkbox or by Anubis? An error, no useful content, or the actual content I want?

m00dy

you can bypass those easily except Google Captcha v3, you need to have your own proxy swarm to make it at scale.

weird-eye-issue

There is no single answer to this, it entirely depends on the exact service and the exact page Most US services like Claude and ChatGPT send a specific user agent that makes it easy to block them and specifically does not try to get around any sort of bot protections Meanwhile other services could u

替代方案: SerpAPI自建爬虫curlpython脚本
查看原文 →