DeepSeek ships Search/Fetch APIs; docs hint at V4.1 Pro launch
teortaxesTex · x · 2026-10-17
DeepSeek's API docs and open platform got key updates: new Search and Fetch endpoints, plus a function-calling stat on the usage page. Unconfirmed, but since web search is only available on V4 Pro (ignored on Flash), many speculate this paves the way for V4.1 Pro.
Key points:
- Pricing: 5 RMB per 1k successful requests for both search and fetch, failures free, tokens billed separately — vs Brave at $5/1k and Tavily/Exa at $5-8
- Free search fees in Claude Code and Codex for the first two weeks
- Requires V4 Pro: 27 RMB/M output tokens at peak (Flash is 8 RMB)
- Codex one-click script defaults websearch off; set it to "live"
- Rate limits: 5 req/s each for search and fetch, per account
- Enable search for news/prices/fresh docs; skip for copywriting, translation, brainstorming
Related event: DeepSeek Launches Search and Fetch APIs at $0.75 per 1,000 Calls(4 posts)→
More from Models
- Distillation angle overrated: frontier reasoning gains mostly come from internal RL, argues analyst — teortaxesTex · 2026-10-17
- Meta's Muse AI stumbles: needs login and virtual browser just to fetch a Marketplace photo — robblatt · 2026-10-17
- Ultra subscriber: Gemini 4 Argon weekly quotas so low they run out in two days — DeryaTR_ · 2026-10-17
- Codex upgrades DSH and live-tests DeepSeek-V4.1-Flash 1017 — cedric_chee · 2026-10-17
- Will Human Brains Soon Fail to Judge Whether New Models Are Actually Better? — arjunrajlab · 2026-10-17
- User Reports Astra Agent Unprompted Finds Sophisticated Security Bugs via Gmail — Tasty-Trip5518 · 2026-10-17