DeepSeek launches Search and Fetch APIs at $0.75 per 1,000 requests
Chinese AI company DeepSeek announced on Oct. 17 that it is offering a Search API and a Fetch API for external developers. Both services are priced at $0.75 per 1,000 successful requests, and free server‑side access is available until 1 a.m. Japan time on Nov. 1, 2026. The launch was reported by GIGAZINE on Oct. 19.
Key points
- DeepSeek's Search and Fetch APIs cost $0.75 per 1,000 successful requests.
- Free server‑side access ends at 1 a.m. Japan time on Nov. 1, 2026.
- APIs integrate with DeepSeek Harness, Anthropic Claude Code, and OpenAI Codex.
The Search API lets applications query DeepSeek’s proprietary web‑search engine, while the Fetch API returns the main text of a supplied URL in markdown format. After locating relevant pages with Search, developers can pull the content with Fetch and feed it into downstream AI tasks such as summarisation or analysis. The APIs are already integrated on the server side of DeepSeek Harness and can be called from Anthropic’s Claude Code and OpenAI’s Codex. On the same day DeepSeek also released a new model, DeepSeek‑V4.1‑Flash‑1017.
DeepSeek frames the move as a way to broaden its developer ecosystem, offering low‑cost, ready‑made search and document‑retrieval functions that many AI agents and tools need. GIGAZINE’s price comparison suggests the fees are cheaper than competing search APIs, though the company warns that actual costs may vary with usage patterns after the free period ends.
Model page: DeepSeek-V4.1-Flash-1017 →
DeepSeek launches Search, Fetch APIs at $0.75 per 1,000 successful requests
digitaltoday.co.kr · 18 October 2026
Loading the full article…
This text was published by digitaltoday.co.kr and written by Jinju Hong. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- WhatsApp MCP lets AI agents read personal chats on Cloudflare Workers · 1 src
- Anthropic consults law firms to develop negotiation norms for AI agents · 3 src
- Opinion: GPT-6.1 Sol may be the best default model for Codex users · 1 src
- Simon Willison releases llm-tools-datasette 0.1.1 · 1 src
- TinyFish provides free search and fetch, benchmark shows $9.30 per 1,000 tasks · 1 src
Comments
via GitHub Discussions