[0.125 / 0.33] v4.1 flash prosperity for all

Hello all! I am building deeprelay.ai - a highly efficient inference platform for open models. We have v4.1 flash, along with other popular models like K3 and GLM 5.3, for one of the lowest, if not lowest, rates on the market. We also serve these at official precision with no additional quality reducing quantization. Our $6 subscription gives 300 million 4.1 flash tokens per month, which I hope is pretty competitive. We just went live today and I wanted to share to see if anyone is willing to help give some feedback in exchange for a trial code. If you are, please reach out and lmk :)

添加评论
点赞收藏
点踩分享查看原文
评论
?
参与讨论