Spotify's Portal Cut Claude Code Token Usage by 90% With a Two-Mode Router
rseroter · x · 2026-09-04
Spotify Engineering's Portal platform cut Claude Code token usage by 90% by routing grunt work to cheap models. The insight: most of what coding agents do is I/O, not reasoning. With AI coding costs projected to exceed average developer salaries by 2028 — and a quarter of engineering leaders already burning $200–$500 per developer monthly on tokens — the fix requires no platform team. Portal's AiKA Modes are declarative agents on ephemeral runtimes (Lambda for agents): define instructions, pick a model like Gemini 2.5 Flash, attach MCP tools, call via CLI or API. The author built a 'bulk-reader' mode to handle multi-file questions cheaply, reserving frontier models for real reasoning.
Related event: Spotify Cuts Claude Code Token Usage by 90% with Dual-Model Routing(2 posts)→
More from coding & agent
- Screenshot table to Excel in PowerShell: LLM only locates, code does the rest — dfinke · 2026-10-21
- One line of PowerShell turns any screenshot table into real Excel data in 4 seconds — dfinke · 2026-10-21
- Screenshot to spreadsheet in 4 seconds with one line of PowerShell — dfinke · 2026-10-21
- A mitm proxy that rewrites robots.txt to Allow: all gets you really far — generativist · 2026-10-21
- Anaconda ships MCP to stop coding agents from hallucinating malicious dependency packages — anacondainc · 2026-10-21
- 5-person team uses Claude and 300+ agents to design 318,484 proteins in 64 hours — 141_1337 · 2026-10-21