Fireworks
@FireworksAI_HQ
The frontier platform for training and inference on open-weights models at scale.
Joined September 2022
304 Following 33.1K Followers
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.
Show more
