956 views · 18 likes · 6 reposts (at collection)
vLLM highlights serving performance as DeepSeek releases DeepSeek-V4.1-Flash-1017
- Who
- vLLM
- What
- reports serving performance DeepSeek-V4.1-Flash on SemiAnalysis AgentX
What happened
DeepSeek announced DeepSeek-V4.1-Flash-1017 with stronger benchmark performance, faster task completion, and shorter outputs than the previous version, available on its website, app, and API. Congratulating DeepSeek, vLLM reports 1.3B tokens per dollar TCO on SemiAnalysis AgentX for DeepSeek-V4.1-Flash, with 830K tok/s per GPU (cached + input + output) at 100 tok/s per user, and 5x agentic throughput since day 0. https://vllm.ai/blog/2026-10-07-deepseek-v41-flash
Why it matters
The post adds serving economics to the model update, connecting shorter outputs and faster task completion with vLLM’s reported throughput under a specified per-user generation rate.
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
Latest daily · Issue 25DeepSeek releases DeepSeek-V4.1-Flash-1017 on its website, app, and APITrending now
- 2Meta Removes Business Terms Language That Raised Website Scraping and AI Training Concerns
- 3Google DeepMind Says Four Gemini 4 Argon Agents Beat Minecraft Without Human Help
- 4Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
- 5Anthropic Says Claude Reconstructed Five NIST Elliptic-Curve Seeds Using a Timestamp-Initialized Generator
Tomorrow at 08:00, a briefing like this arrives in your inbox.
The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue · 2026-10-18