LectureRechercheRadarCadre d'investissement
Connexion / Inscription
← Retour à la lecture
ActualitésSujet · DeepSeek搜索接口Matériel1 min de lectureRédaction DisconfirmAI

DeepSeek Opens In-House Search API to Developers for Real-Time Web Retrieval

DeepSeek has opened its internal search engine to external developers via new APIs, enabling real-time web retrieval and content fetching for AI agents.

Vérifié 2026-10-18 00:14 GMT+8

On October 17, 2026, DeepSeek announced in its API update log that it is opening its in-house search engine to external developers. Previously serving only DeepSeek's own web interface and chat API, the search capability is now available as independent "Search" and "Fetch" tools.

According to official documentation, the DeepSeek search engine is an AI-native general-purpose search engine that indexes hundreds of billions of web pages globally, supports multilingual search, and returns highly relevant and authoritative results in real time. It employs strict detection mechanisms to filter out SEO spam, GEO manipulation, and low-quality AIGC content, ensuring trustworthy information for users and LLMs.

The release includes two main interfaces: the Search API finds web pages for a query and returns structured results, while the Fetch API grabs a single page and returns it as Markdown. This allows developers building AI agents or Retrieval-Augmented Generation (RAG) systems requiring live web data to use DeepSeek's native search directly, without integrating third-party search providers.

Media reports indicate pricing at $0.75 per 1,000 calls for each endpoint, billed per successful request. Failed requests, empty results, and timeouts are not billed. Server-side tool calls made through platforms like DeepSeek Harness, Claude Code, or Codex are free until billing starts on November 1, 2026.

Sources

Connexion / Inscription
LectureRechercheRadarCadre d'investissement
api-docs.deepseek.com
↗
Sujet

DeepSeek搜索接口

中国杭州的 DeepSeek 于 2026 年 10 月 17 日正式向开发者开放其自研搜索引擎驱动的 Search 与 Fetch API,旨在为 AI 智能体提供实时网页检索能力。该服务定价为每千次成功请求 5 元人民币(约 0.75 …

4 étapes3 piècesMis à jour 2026-10-23 18:06

Comment on en est arrivé là

  1. 2026-09-10DeepSeek 发布 V4.1-Flash 模型,作为新架构系列中最小尺寸的多模态模型,并调整 API 价格。api-docs.deepseek.com ↗
  2. 2026-10-15DeepSeek 发生近 5 小时 API 服务中断,官方随后道歉并向用户发放补偿额度。siliconangle.com ↗
  3. 2026-10-17DeepSeek 上线 Search 与 Fetch API,明确每千次请求 5 元的计费标准及每秒 5 次的限流规则;同时更新 V4.1-Flash-1017 模型。ithome.com ↗

Ce qui reste non résolu

  • 11 月 1 日免费期结束后,开发者对付费调用的实际接受度如何?
  • DeepSeek 自研搜索引擎在处理 SEO 垃圾内容和低质量 AIGC 时的长期准确率能否维持?
  • V4.1-Flash-1017 版本的具体性能提升幅度是否会在后续基准测试中得到独立验证?

Également dans ce fil

  • DeepSeek Releases Updated V4.1-Flash Model, Claims Faster Task Completion and Opens Search API2026-10-19
  • DeepSeek Launches Search and Fetch APIs at 5 Yuan per 1,000 Requests, Free for Select Tools Until Nov 12026-10-17
Lire le sujet complet →
Continuer la recherche →