Svmuu News: Brian Armstrong, CEO of Coinbase, posted on X stating that Coinbase has reduced AI spending by nearly 50% while token usage continues to grow, by optimizing default settings, routing, and caching strategies.
Specific measures include: switching the default models to open-source pre-trained models such as GLM 5.2 and Kimi 2.7—91% of employees had never previously reached the usage limit; preprocessing prompts within a custom system and automatically routing them to the most suitable model, enabling differentiated handling of planning and execution tasks;improving cache hit rates—LibreChat’s cache hit rate increased from 5% to 60%; streamlining context management by opening new sessions when switching tasks and narrowing the scope of file contexts; and enhancing spending visibility, allowing engineers to freely choose models while assuming responsibility for the corresponding impact on costs.