Press Space to continue
Blended effective price per token can keep falling for a long
Press Space to continue
Blended effective price per token can keep falling for a long time even if the list prices of new models remain flat or even increase a bit. Cache is king
OpenRouter@OpenRouter3d ago
Cache rates across the AI landscape have gotten markedly better in 2026. We saw an 85% median cache rate in agentic requests across OpenRouter last month, up from 65% in the beginning of the year. And the vast majority of providers now serve agentic cache at 70% or higher.
