Stelladocs
Commands

stella stats

Summarize cost, tokens, and resolve rate per provider/model from local telemetry.

Read back what your runs actually cost. stella stats summarizes cost, tokens, and resolve rate per provider and model from the local telemetry store — $/resolved-task receipts, computed entirely on your machine.

Synopsis

stella stats [--format <table|json|csv>] [--provider <id>]

What it does

stella stats reads <workspace>/.stella/store.db — the embedded SQLite store every run writes to — and aggregates it per provider/model: total tokens, total cost, and how often work resolved. It makes no network calls and needs no API key; it only reads local telemetry.

Flags

FlagMeaning
--format <table|json|csv>Output format. table (default) prints an aligned table with a TOTAL row; json and csv are for piping into other tools.
--provider <id>Only include executions for this provider id (e.g. zai, anthropic, local).

Examples

Print the aligned summary with a total row:

stella stats

Just one provider, as CSV for a spreadsheet:

stella stats --provider anthropic --format csv > anthropic-spend.csv

Emit JSON for a dashboard or a jq pipeline:

stella stats --format json | jq '.[] | {model, total_cost_usd, resolve_rate}'

The store is a real SQLite file. Beyond stella stats you can query it directly with any SQLite client — see Telemetry & budget.

Stella is totally free and open source, dual-licensed MIT or Apache 2.0— your choice: MIT's three-paragraph simplicity, or Apache 2.0's explicit patent grant that enterprises prefer. Use it, fork it, embed it, ship it — no account, no phone-home, no strings. What that means →

On this page