Release55d ago
DeepSeek opens V4.1 Flash mid-build API beta: model deepseek-v4.1-flash-expires-on-0910, priced like V4 Flash
DeepSeek is running a short V4.1 Flash intermediate API beta. Keep the same base_url and set model to deepseek-v4.1-flash-expires-on-0910. DeepSeek describes a new architecture with native multimodality that is faster and cheaper; billing matches deepseek-v4-flash, about 20 concurrent requests per account, with the test window roughly through Sep 10 (expires-on-0910 in the model id).
Tooling2d ago
DeepSeek Harness team open-sources dsh-superagent, a proactive coding agent prototype for a single GitHub repo, alongside its Super-agent architecture article
On Oct 31, deepseek-ai open-sourced dsh-superagent-prototype on GitHub under the MIT license: a proactive coding agent that runs as a DeepSeek Harness bundle, lives on one GitHub repository and can optionally listen to Feishu. When an allowed person asks for work, it opens a work item, works in its own session and directory, and answers in the original conversation, for example with a pull request. The README states it is a research prototype, not an official DeepSeek product. The companion article, Exploring Super-agent Design, proposes a two-layer Router-Worker architecture; the team test, as reproduced by media, reports a p95 completion time of 15.7 minutes versus 29.5 minutes for a single-session setup.
Release54d ago
DeepSeek launches V4.1-Flash: 552B MoE asymmetric encoder-decoder, leaner KV cache, open weights
DeepSeek introduced DeepSeek-V4.1-Flash—the smallest model in its new family with native vision. It is a 552B MoE with a Causal Encoder–Decoder (8B active on input, 16B on output), claims benchmarks ahead of flagships including V4-Pro, shrinks KV cache to ~1/4 HBM and ~1/8 SSD vs prior gen, and published HF weights plus a tech report.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.