https://www.darius.wiki/en/topics/deepseek/DeepSeek's open V4 model family, the DeepSeek API, and its agent-facing Harness plus Search and Fetch APIsenSun, 18 Oct 2026 00:00:00 GMThttps://www.darius.wiki/en/daily/2026-10-18/deepseek-v4-1-flash-1017/https://www.darius.wiki/en/daily/2026-10-18/deepseek-v4-1-flash-1017/Sun, 18 Oct 2026 00:00:00 GMTModel releaseA minor update to V4.1-Flash with clear gains on coding and agent benchmarks, and DeepSeek says it also finishes faster with shorter outputs. How much it moved and where it sits next to closed models. Take: Put it next to Beam on 10-17 and Muse Spark Open on 10-16 and open coding models closed in on closed ones all week. I'd point Claude Code at it on a batch of real tasks from my own repos, checking whether shorter outputs still mean complete changes; note the missing Jinja template before self-hosting, and don't force a generic one onto it.https://www.darius.wiki/en/daily/2026-10-18/deepseek-search-fetch-api/https://www.darius.wiki/en/daily/2026-10-18/deepseek-search-fetch-api/Sun, 18 Oct 2026 00:00:00 GMTToolsDeepSeek turns its in-house search engine into a developer API, launched alongside the new model. Pricing, the free period, and which agent tools it is courting. Take: Agent web access now has a plainly priced option from a Chinese provider. For a content backend that looks things up, like PandaClaws, use the free window before October 31 to compare hit rate and latency against your current search; before adopting it, count searches per task, because that number runs away easily in agents.