## Current pipeline

- `pnpm protocol:gen`

- writes JSON Schema (draft‑07) to `dist/protocol.schema.json`

- writes JSON Schema (draft-07) to `dist/protocol.schema.json`

- `pnpm protocol:gen:swift`

- generates Swift gateway models

- `pnpm protocol:check`

## Where it shows up

- `/status` in chats: emoji‑rich status card with session tokens + estimated cost (API key only). Provider usage shows for the **current model provider** when available as a normalized `X% left` window.

- `/status` in chats: emoji-rich status card with session tokens + estimated cost (API key only). Provider usage shows for the **current model provider** when available as a normalized `X% left` window.

- `/usage off|tokens|full` in chats: per-response usage footer (OAuth shows tokens only).

- `/usage cost` in chats: local cost summary aggregated from OpenClaw session logs.

- CLI: `openclaw status --usage` prints a full per-provider breakdown.

- CLI: `openclaw channels list` prints the same usage snapshot alongside provider config (use `--no-usage` to skip).

- macOS menu bar: “Usage” section under Context (only if available).

- macOS menu bar: "Usage" section under Context (only if available).

## Providers + credentials

Run a persistent OpenClaw Gateway on a Hetzner VPS using Docker, with durable state, baked-in binaries, and safe restart behavior.

If you want “OpenClaw 24/7 for ~$5”, this is the simplest reliable setup.

If you want "OpenClaw 24/7 for ~$5", this is the simplest reliable setup.

Hetzner pricing changes; pick the smallest Debian/Ubuntu VPS and scale up if you hit OOMs.

Security model reminder:

- Full testing kit (suites, live, Docker): [Testing](/help/testing)

- Update and plugin package validation: [Testing updates and plugins](/help/testing-updates-plugins)

- `pnpm test:force`: Kills any lingering gateway process holding the default control port, then runs the full Vitest suite with an isolated gateway port so server tests don’t collide with a running instance. Use this when a prior gateway run left port 18789 occupied.

- `pnpm test:force`: Kills any lingering gateway process holding the default control port, then runs the full Vitest suite with an isolated gateway port so server tests don't collide with a running instance. Use this when a prior gateway run left port 18789 occupied.

- `pnpm test:coverage`: Runs the unit suite with V8 coverage (via `vitest.unit.config.ts`). This is a default-unit-lane coverage gate, not whole-repo all-file coverage. Thresholds are 70% lines/functions/statements and 55% branches. Because `coverage.all` is false and the default lane scopes coverage includes to non-fast unit tests with sibling source files, the gate measures source owned by this lane instead of every transitive import it happens to load.

- `pnpm test:coverage:changed`: Runs unit coverage only for files changed since `origin/main`.

- `pnpm test:changed`: cheap smart changed test run. It runs precise targets from direct test edits, sibling `*.test.ts` files, explicit source mappings, and the local import graph. Broad/config/package changes are skipped unless they map to precise tests.

- `source ~/.profile && pnpm tsx scripts/bench-model.ts --runs 10`

- Optional env: `MINIMAX_API_KEY`, `MINIMAX_BASE_URL`, `MINIMAX_MODEL`, `ANTHROPIC_API_KEY`

- Default prompt: “Reply with a single word: ok. No punctuation or extra text.”

- Default prompt: "Reply with a single word: ok. No punctuation or extra text."

Last run (2025-12-31, 20 runs):

title: "Token use and costs"

---

# Token use & costs

OpenClaw tracks **tokens**, not characters. Tokens are model-specific, but most

OpenAI-style models average ~4 characters per token for English text.

Use these in chat:

- `/status` → **emoji‑rich status card** with the session model, context usage,

- `/status` → **emoji-rich status card** with the session model, context usage,

last response input/output tokens, and **estimated cost** (API key only).

- `/usage off|tokens|full` → appends a **per-response usage footer** to every reply.

- Persists per session (stored as `responseUsage`).

For a full knob-by-knob guide, see [Prompt Caching](/reference/prompt-caching).

For Anthropic API pricing, cache reads are significantly cheaper than input

tokens, while cache writes are billed at a higher multiplier. See Anthropic’s

tokens, while cache writes are billed at a higher multiplier. See Anthropic's

prompt caching pricing for the latest rates and TTL multipliers:

[https://docs.anthropic.com/docs/build-with-claude/prompt-caching](https://docs.anthropic.com/docs/build-with-claude/prompt-caching)