DeepSeek V4.1 Flash 1017 Reaches 244 Tokens/sec and Opens Web Tools via API
DeepSeek says V4.1 Flash 1017 generates 244 tokens per second, outpacing GPT-6.1 Sol in Ultrafast mode, and now exposes web search and page-loading tools through an API.
DeepSeek V4.1 Flash 1017 generates 244 tokens per second, surpassing even GPT-6.1 Sol in Ultrafast mode, which is available through a $500/month plan.
DeepSeek has also given developers access to its own web-search and page-loading tools through an API. Until October 31, the tools can be used for free via the official DeepSeek Harness; after that, pricing will be $0.75 per 1,000 requests.
Why it matters
AnalysisThe speed claim matters for latency-sensitive agents and coding workflows, while the API expansion reduces the need for separate search and scraping services.
Discuss in community
Share your questions and insights with developers