Deepseek V4 Flash is now ~#2 open weight model to Kimi K3 and >50x cheaper

https://preview.redd.it/h7zv5tb3tmgh1.png?width=2854&format=png&auto=webp&s=507380e8f862c18f10f7c5c84da9e8d1c59139b0 Deepseek's new flash model is unexpectedly cheap and high-performing across useful benchmarks. It's priced at $0.09 / $0.18 per 1M. Truly "intelligence too cheap to meter". See

中文全文翻译正在补齐，可先查看下方英文原文。

https://preview.redd.it/h7zv5tb3tmgh1.png?width=2854&format=png&auto=webp&s=507380e8f862c18f10f7c5c84da9e8d1c59139b0 Deepseek's new flash model is unexpectedly cheap and high-performing across useful benchmarks. It's priced at $0.09 / $0.18 per 1M. Truly "intelligence too cheap to meter". See