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, escalating only for the hard, correctness-critical work. Estimate that below, then see exactly where the 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.
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 cheaperapp peek # scan all history
cheaper peek --days 30 # just the last 30 days
cheaper peek --harness claude-code # one tool · add --json to script it
| 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) | |||
Illustrative output. The real command reads your own logs locally; the web tracker above is the same math without the file access.
Point the tool at the Cheaper gateway (it speaks both the Anthropic and OpenAI-compatible APIs), then watch the monitor turn the estimate above into measured numbers:
npx cheaperapp install --all
cheaper gateway start
export ANTHROPIC_BASE_URL=http://localhost:8787
cheaper monitor