DeepSeek V4.1 Flash: 1T tokens in 24 hours on OpenRouter, and is on pace for the biggest 48 hours of any paid model launch at ~2.8T. 90% of those toke...

AI 摘要

模型生成，可能有偏差；请以原文为准

OpenRouter 官方公布 DeepSeek V4.1 Flash 上线数据，该模型在平台发布 24 小时内 token 调用量达到 1T，预计 48 小时内将达约 2.8T。统计显示其中 90% 的 token 为缓存读取，市场定价约为每百万 token 0.006 美元，价格约为同类模型 GLM-5.3 Flash 的五分之一。该数据反映出低价缓存机制对开发者调用量的显著拉动效应。

正文

DeepSeek V4.1 Flash: 1T tokens in 24 hours on OpenRouter, and is on pace for the biggest 48 hours of any paid model launch at ~2.8T.

90% of those tokens were cache reads, priced by the market at ~$0.006/M, 5x cheaper than comparable models like GLM-5.3 Flash

部署·工程行业动态DeepSeek

在原站阅读 · x.com