Press Space to continue
Strategies to combat rising AI token costs
Press Space to continue
So, at your company, what are you doing about the spiking token prices? Approaches I hear: 1. Inference routing - route more basic workloads to a LOT cheaper APIs or providers 2. Use cheaper open models for inference (eg Fireworks, Baseten etc) 3. Default model: cheap one
open on x · 1 viewViews and clicks count once per visitor per day. Clicks are opens of this post on X.