Dang, not even Spotify care enough to not write AI slop articles.
We’re fucked.
Portal by Spotify cut my Claude Code token usage by 90%
21–30 of 153 posts
Re: Portal by Spotify cut my Claude Code token usage by 90%
#22It doesn't work well in practice.
Try it yourself, use a big model like Opus or Sol to implement everything by first making a plan using plan mode.
Then try distributing the task to a cheaper models like Luna Max or Gemini Flash 3.8.
During planning, the big model already reads the relevant files in context, while giving a smaller model a slice of work itself requires the big model to reason about the task distribution, review, etc.
So do you really save on tokens?
Re: Portal by Spotify cut my Claude Code token usage by 90%
#23So 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.
> So this is just delegating certain work to dumber models? I certainly wouldn't use Gemini 2.5 Flash (!!?) for code writing as suggested.
Why not, though? I started using OpenCode + GitHub Copilot, but I burned through my Claude Sonnet quota in just three days. I switched to GPT-5.4-mini, which uses far fewer tokens, and it’s often just as good as Sonnet. I think optimizing token usage is a good exercise. We often assume a model will be terrible, when it really isn’t.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#24It doesn't work well in practice. Try it yourself, use a big model like Opus or Sol to implement everything by first making a plan using plan mode. Then try distributing the task to a cheaper models like Luna Max or Gemini Flash 3.8. During planning, the big model already reads the relevant files in context, while giving a smaller model a slice of work itself requires the big model to reason about the task distributi…
Maybe not, but I like to review the plan anyway so that I'm less surprised by what it actually did.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#25It doesn't work well in practice. Try it yourself, use a big model like Opus or Sol to implement everything by first making a plan using plan mode. Then try distributing the task to a cheaper models like Luna Max or Gemini Flash 3.8. During planning, the big model already reads the relevant files in context, while giving a smaller model a slice of work itself requires the big model to reason about the task distributi…
> Try it yourself, use a big model like Opus or Sol to implement everything by first making a plan using plan mode.
When I do this, I can have it use cheap subagents with models like Luna to read the relevant files.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#26Dang, not even Spotify care enough to not write AI slop articles. We’re fucked.
To be fair, Spotify was a slop factory long before LLMs started doing it
Re: Portal by Spotify cut my Claude Code token usage by 90%
#27It doesn't work well in practice. Try it yourself, use a big model like Opus or Sol to implement everything by first making a plan using plan mode. Then try distributing the task to a cheaper models like Luna Max or Gemini Flash 3.8. During planning, the big model already reads the relevant files in context, while giving a smaller model a slice of work itself requires the big model to reason about the task distributi…
> Try it yourself, use a big model like Opus or Sol to implement everything by first making a plan using plan mode. When I do this, I can have it use cheap subagents with models like Luna to read the relevant files.
Do you have the cheap models summarize the files? How do they get the relevant information to the bigger models?
Re: Portal by Spotify cut my Claude Code token usage by 90%
#28It 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 ha…
You can also use hooks to force the use of subagents for this. The stack here is entirely unnecessary
Re: Portal by Spotify cut my Claude Code token usage by 90%
#29Isn't this a somewhat standard multi-model setup? there's nothing ground breaking here, just delegate claude to plan -> smaller model for implementation.
Very standard in all coding harnesses/models I've worked with, with the bonus that everything listed in the "What doesn't work in Portal by Spotify" section still works. I've been watching Opus spin off work to Fable and Sonnet as appropriate all day.
Re: Portal by Spotify cut my Claude Code token usage by 90%
#30Oh dear, why does this website override scrolling behavior?
My first thought too! I couldn't put up with it. Left quickly.