Savings tracker

Gemini savings tracker

Pick your tool, set how your work splits across task difficulty, and see your annual cost reduction — broken down by task complexity, by model, and by supported tool.

Most bills come from one habit: reaching for the top-tier model on every call. Cheaper triages each request and routes it to the cheapest model that still clears the bar — capped by whatever model you asked for, so it only ever downgrades or matches, never spends more. Hard, correctness-critical work (concurrency, security, proofs) is protected from being downgraded, not escalated past what you requested. Estimate that below, then see exactly where the money goes.

Estimate your savings

Tool

Your current monthly spend on Claude Code ($)

Your task mix — how your requests split by difficulty

Simple · boilerplate, edits, renames, lookups55%

Moderate · multi-file changes, refactors, tests30%

Complex · architecture, security, tricky bugs, proofs15%

Estimated annual savings

Baseline assumes you run the top-tier model on every request. Prices are illustrative output rates ($/Mtok) with equal token weight per task; your real numbers come from the gateway monitor. Simple work drops to a model ~5–20× cheaper; complex work stays on the frontier.

Where your money goes

Same estimate, three views of the cost reduction. Use the projection slider to scale it from a single month out to two years — it defaults to a full year.

1 moProjection: 12 months (1 year)24 mo

Test it on your real history

The estimate above is a model. Want your actual numbers? After installing, run one local, read-only command — cheaper peek scans your existing .claude, .codex, … chat logs and reports exactly what routing would have saved, in tokens and dollars. Nothing leaves your machine; it classifies prompt text only, never your files or tool output.

npx cheaper peek                 # scan all history
cheaper peek --days 30              # just the last 30 days
cheaper peek --harness gemini-cli   # one tool  ·  add --json to script it

Gemini CLI reading is experimental — peek parses what it can from the tool's config directory and fabricates nothing it can't find.

cheaper peek — what adaptive routing would have saved

Example output — not your data

scanned last 30d across your harness chat logs

harness	calls	downgradable	tokens	you’d save
● Claude Code	1,284	876 (68%)	18.4M	$41.20
◐ Codex	412	223 (54%)	5.1M	$7.80
○ Cursor	DB-backed (not yet readable)

Total 1,696 calls · 1,099 downgradable · from you 1,204 / sub-agents 492

Spent on record $71.40

Could have saved $49.00 (69% off) · 14.9M tokens re-routable

Annualized $596/yr (extrapolated from 30d)

Example output — not your data

Biggest opportunities (top-tier calls that didn’t need it):

$0.38 opus→haiku you rename getUser to fetchUser across the repo

$0.31 opus→haiku sub-agent list the files in src/components

Example output shown above — not your data. The real command reads your own logs locally; the web tracker above is the same math without the file access.

How it works with Gemini

Today, this needs Gemini's OpenAI-compatibility mode. Gemini's native generateContent API isn't OpenAI-shaped, so the gateway can't route it yet — a native adapter is on the roadmap. Switch Gemini CLI (or your Gemini client) to its OpenAI-compatible mode and point its base URL at the gateway:

npx cheaper install --all
cheaper gateway start
export OPENAI_BASE_URL=http://localhost:8787/v1
cheaper monitor

The gateway's OpenAI-compatible route forwards to api.openai.com by default — for these calls to reach Gemini's servers rather than OpenAI's, also set OPENAI_UPSTREAM_URL to Gemini's OpenAI-compatibility endpoint and OPENAI_MODEL_CHEAP/MID/TOP to Gemini model ids.

Read the docs → · See every supported tool →