DeepSeek releases DeepSeek-V4.1-Flash-1017 with claimed performance and cost improvements

What happened

DeepSeek announced DeepSeek-V4.1-Flash-1017, claiming stronger benchmark performance, faster task completion, and shorter outputs than the previous version, now available on its website, app, and API. Nathan Lambert calls the naming scheme “bonkers” and the benchmark improvement big, suggesting it could prove stronger than GLM 5.3 with vision built in. “The King of open weights is back?”

The story so far

DeepSeek released DeepSeek-V4.1-Flash-1017 on its website, app, and API, and Ollama has now added it to Ollama Cloud with what Ollama says is US-based hosting and zero data retention. DeepSeek says the update improves benchmark performance, completes tasks faster, and produces shorter outputs than the previous version. It says the model is optimized for DeepSeek Harness, Tencent CodeBuddy, WorkBuddy, and other tools, and recommends DeepSeek Harness v0.2.1-rc.1 or later. Ollama provides access through the model tag deepseek-v4.1-flash:1017-cloud, including integrations with Claude Code and OpenCode. Ollama describes the model as strong on agentic tasks and cheaper per task. Separately, vLLM reports serving DeepSeek-V4.1-Flash on SemiAnalysis AgentX at 1.3 billion tokens per dollar of total cost of ownership and 830,000 tokens per second per GPU, counting cached, input, and output tokens, at 100 tokens per second per user. Those figures apply to DeepSeek-V4.1-Flash, rather than specifically the 1017 update. Baoyu reports that the web search API will cost 5 yuan per 1,000 calls starting November 1.

Keep reading

Trending now

1. 2Google DeepMind Says Four Gemini 4 Argon Agents Beat Minecraft Without Human Help
2. 3Meta Removes Business Terms Language That Raised Website Scraping and AI Training Concerns
3. 4Anthropic Says Claude Reconstructed Five NIST Elliptic-Curve Seeds Using a Timestamp-Initialized Generator
4. 5Meta Releases Muse Spark Open With Mac and Cloud Support, Leading US Open-Weight Index