DeepSeek Launches Search and Fetch APIs for Real-Time Web Content

By AI123

On October 17, DeepSeek announced the general availability of its Search and Fetch APIs. Both interfaces are powered by DeepSeek's self-developed search engine and provide real-time web content for agent and RAG applications.

The Search API queries the web and returns structured results, while the Fetch API retrieves a single page and returns its title and body as Markdown. Both are raw JSON APIs with a base URL of api.deepseek.com, using the same Bearer authentication as the DeepSeek API.

Pricing is based on successful requests at 5 yuan per 1,000 calls. A charge is incurred only when Search returns a non-empty result list, or when Fetch returns page content with an HTTP 200 status. Failed requests, empty results and timeouts are not billed, and the number of results does not affect the price.

Each account is limited to 5 queries per second for Search and Fetch separately. The Search query has a maximum of 128 characters, and the number of returned results can be selected from 1 to 50, with a default of 10. Each result includes title, URL, summary, a longer model-oriented summary, optional full text, publication date, reranking score and authority rating.

Additionally, until November 1, 2026, searches triggered through Claude Code's Web Search tool or Codex's web_search feature will not incur Search fees.

Explore topicsAIDeepSeekModels

Sources

View all