DeepSeek Releases Updated V4.1-Flash Model, Claims Faster Task Completion and Opens Search API

Chinese AI startup DeepSeek released an updated version of its V4.1-Flash model, DeepSeek-V4.1-Flash-1017, on October 18. According to the model card on Hugging Face, this "minor update" aims to reduce task execution time and output length, though DeepSeek did not disclose the specific extent of improvement. In DeepSeek's own testing on the DeepSWE v1.1 software engineering benchmark, the new version resolved 77% of tasks, up from 74.2% for the September release.

In addition to the model update, DeepSeek opened its internal search engine to external developers via a Search API that returns up to 50 ranked web results per query. A companion Fetch API converts single web pages to Markdown. Both services cost 75 cents per 1,000 successful requests. Notably, calls made through DeepSeek Harness, Anthropic's Claude Code, or OpenAI's Codex are free until November 1.

DeepSeek stated that the update was tuned for agent software, including its own DeepSeek Harness tool and two Tencent products: the CodeBuddy coding assistant and WorkBuddy, a desktop agent for office work. The updated model is now live in DeepSeek's web and mobile apps, and API customers can access it via the existing deepseek-flash model ID at unchanged prices.