DeepSeek search and fetch – $0.75 per 1000 successful requests
- ID
- 36754
- Status
- summarized
- Published
- 18 Oct 2026, 2:50 PM
- Fetched
- 18 Oct 2026, 7:49 PM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://api-docs.deepseek.com/guides/search/
- Source URL
- https://hnrss.org/best
Summary
- Score
- 7.5
- Created
- 18 Oct 2026, 7:49 PM
- Tags
- Audience
- developersai_ml_learnersai_agent_usersvibe_coderssaas_founders
What happened
DeepSeek shipped two raw JSON endpoints under its existing API key auth: POST /v1/tools/search (in-house search engine, returns structured results) and POST /v1/tools/fetch (single page returned as Markdown). Search takes count 1–50 (default 10), an optional need_content flag that inlines page content in the same call, an ori_question field for query rewriting, an IP-based localization field, and supports site:/ -site: operators. Pricing listed in the title is $0.75 per 1,000 successful requests; the HN thread drew 223 points and 104 comments.
Why it matters
At $0.75 per 1,000 successful requests that's roughly $0.00075 per search — worth pricing against whatever you currently pay Tavily, Exa, or Brave inside an agent loop. Setting need_content=true collapses search+fetch into one request, so you drop a round trip and a second billable call per agent step; the localization field lets you pass an IP to bias results toward Malaysian sources instead of getting US-default rankings. Check the 'successful requests' definition before you budget, since failed or empty searches may bill differently.
Discussion angle
Do the per-agent-run cost math live: search calls per task × $0.00075 versus your current provider, and whether need_content=true is good enough to replace a separate fetch/scrape step in your RAG pipeline.