AI & Cloud Infrastructure
September 8, 2026Spotify cut Claude Code tokens 90%: copy the pattern
Spotify routes bulk file reads and boilerplate generation out of Claude Code to a cheaper worker model, cutting Claude token usage on those reads by 90% in tests on a Java monorepo. The pattern needs no Portal licence: Claude Code hooks, two wrapper scripts and a flash-class model in Microsoft Foundry rebuild it inside your own Azure tenant, with the boundaries Spotify itself draws around editing and reasoning.
Claude Code
Spotify
AI Coding Agents
Token Costs
Gemini Flash
Microsoft Foundry
Backstage
Model Routing
Prompt Caching
By Falak Mahmood