Spotify's Portal cut my Claude Code token usage by 90%
Portal by Spotify cut my Claude Code token usage by 90%
An engineer at Spotify shares how they slashed Claude Code token consumption by 90% using Portal's AiKA Modes. By routing bulk file reads and boilerplate code generation to cheaper models like Gemini 2.5 Flash, they saved thousands of tokens on tasks that don't require frontier-level reasoning. The setup involves two declarative modes, a Claude Code plugin with hooks and skills, and results in significant cost savings without sacrificing quality for complex reasoning tasks.
Most of what an AI coding agent does for me isn't thinking. It's I/O.
- schainks
It takes true corporate dedication to publish technical thought leadership on a page that actively fights your ability to read it.
- steveBK123
What great productivity gains are Spotify achieving in making their product worse?
- ricardobeat
No mention of correctness or task success rate. This only works if the subagent model is much cheaper than the one running your session, which means it will probably be mistaken a lot more often [1] about what the code does. Routing purely on size tells you nothing about code complexity.
On top of that, saving 90% of input tokens != saving 90% "of tokens", output is wildly more expensive.
[1] especially if it's a really old model like Gemini 2.5!
- solenoid0937
So this is just delegating certain work to dumber models? I certainly wouldn't use Gemini 2.5 Flash (!!?) for code writing as suggested.
I've never had an issue with Codex or Claude reading massive files, they're really good at precise greps.
- alastairr
Does anyone even review these blog posts before they get published? If nobody in the company can be bothered to review it, I don't know why they expect anyone to persevere with the AIphorisms
- pmdr
I wish websites would stop messing with the scrolling behavior.
- jnwatson
It cuts token usage because they are using a different service with a different token budget for the reader/code writer tasks.
You can also just delegate this to subagents with Claude Code (though you have a more limited choice of models unless you swap the cheaper models via OpenRouter).
I'm OK using a dumb model as a smart grep, but the whole point of using the frontier models is using their intelligence for the hard stuff like coding.
- khaki54
The downside of reading posts about the practical application of AI is that the practioner often uses AI to write it. I don't know why AI prose is so hard to read in the browser. I don't have any problem when reading off my TUI