DeepSeek released the new model V4.1-Flash-1017, and DeepSeek Harness was upgraded to 0.2.1

DeepSeek released a new model, DeepSeek-V4.1-Flash-1017. The company says it is specifically optimized for DeepSeek Harness, improving task performance while shortening runtime and reducing token consumption. The new model focuses on "wish-style programming," based on self-feedback reinforcement learning, and can generate a runnable project from a single sentence. Full capabilities require upgrading DeepSeek Harness to version 0.2.1-rc.1 or above. At the same time, it also opened its self-developed Search and Fetch APIs, priced at 5 yuan per thousand successful requests, free until November 1.