slice sits in front of every AI call your team makes, routes the easy ones to cheaper models, and cuts the bill before it runs away.
measured · the same 50 prompts, sent direct and through slice
About three minutes. You sign in once with GitHub, then point your tools at slice.
(like this) means a value you fill in with your own. Everything else you can copy as-is.
slice is a small open-source package. Clone the repo and install it, and the slice command lands on your path.
$ git clone https://github.com/jjk30/slice.git && cd slice && pip install -e .
Run slice login. slice shows you a short code. Open github.com/login/device, sign in to GitHub, paste the code, and click Authorize. That is the whole login, no password typed in the terminal.
Why GitHub? You already have it, slice never stores a password, and it signs you in right from the terminal, where slice lives.
$ slice login slice needs to connect to your GitHub account. 1. copy this code WXYZ-1234 2. open https://github.com/login/device 3. paste it, then click Authorize waiting for you to authorize... ✓ signed in as (your-github-username) ✓ your slice key is ready
Set one environment variable so your AI tools send their calls through slice. From here slice routes, caches, and meters every request. No key to paste, your login already set that up.
export ANTHROPIC_BASE_URL=https://api.sliceapp.dev
That is it. Keep coding the way you already do. Every call now flows through slice, and you can watch spend, savings, and budgets live on your slice dashboard.
Open source. slice is yours to read line by line, or to run on your own box. It only reads the calls passing through it, never your codebase.
s3://acme-user-uploads is open to the whole internet and holds files that look like IDs and passports. slice caught it before anyone else did.Set a budget. The moment a team crosses the line, slice buzzes you on WhatsApp and email, with the number, the cause, and how long you have.
Pick the channel, set the number, slice does the buzzing. Email and WhatsApp today, Slack next.
The idea showed up while I was craving a slice of cake. The name stuck, and so did the problem.
All through 2026 I kept reading the same story: great AI tools, adopted fast, billed per token with no ceiling and nobody watching the meter. Uber torched its year's coding budget by April. Amazon burned $1.8M on a single task. That is not a tooling problem. It is a missing brake.
So I built the brake. slice meters every call, routes the easy ones to cheaper models, caches the repeats, and cuts you off before the invoice does.
It is early, and I would rather say so than pretend. One person, deploying now. Try it on your own machine and judge it for yourself.
Leaderboards pushed Claude Code adoption. The CTO said he was back to the drawing board, the budget already blown away.
Internal metrics showed a single job running roughly 860% over its budget, a catastrophically expensive blunder.
The tool caught on faster than budgets could take, so Microsoft cancelled most direct licenses and moved to Copilot CLI.
For his team, the cost of compute is “far beyond the costs of the employees.” Usage-based bills keep outrunning the plan.
Free and open source. Three commands from clone to your first metered request.
Free · open source