Fireworks
@FireworksAI_HQ
The frontier platform for training and inference on open-weights models at scale.
加入 September 2022
304 正在关注 33.1K 粉丝
Many assume that agent spend goes toward output tokens.
When we ran DeepSWE on Astra vs. DeepSeek V4.1-Flash, input tokens outnumbered output 174 to 1. 99.6% were cache hits. Those hits are 60% of the bill.
Net result? Same quality. $0.43/task vs $6.52.
显示更多
