Slash Tokens

For anyone building with LLMs. 4.8 KB WASM. Sub-millisecond. Zero dependencies.

Models change. Windows grow. Slash adapts — you keep building.

Run it in a project that already calls an LLM. An empty folder prints that nothing was found — that's normal.

Intercepts fetch() to Anthropic, OpenAI, xAI, and Google endpoints. Estimates tokens before the call leaves your machine. Sub-millisecond. Non-blocking.

[slash] Anthropic claude-sonnet-5 | 47,000 tokens | $0.0940 | OK

preflight is analysis (every cheaper model, all providers). preflightRoute is the routing decision — same provider only. They answer different questions.

check . options // cheaper models across providers — not a route

Fully typed. Do not use check.options[0] as the route — that list is cross-provider on purpose.

The engine underneath. 4.8 KB Zig-compiled WASM, calibrated against real provider tokenizers — not a flat chars/4 guess.

Safe pre-check, not a perfect count. Pre-call, you only need go/no-go.

Live ladder as of 2026-08-25. Generic aliases ( claude-opus , gpt-5.4 , grok-4.20 , …) still resolve. Don't see yours? Open an issue.

Hosted dashboard is ordinary SaaS: $39/mo or $390/yr for the data, not a cut of savings. One-person key: mcpaas.live/slash/setup

TypeScript SDK tests via cd npm && bun test . Zig coverage includes adversarial cases (CJK, emoji, binary, base64, thresholds).