FAQ

What is tokenolo?

A local proxy for Claude Code (and Codex). It runs on your machine (127.0.0.1) and forwards every request to the model with your own key. The only thing it changes is your prompt text, where it removes redundant filler — removal-only, so meaning is preserved. Your files, tool output and history are forwarded untouched, and nothing is stored.

Which coding agents does it work with?

Drop-in for Claude Code and Codex. tokenolo is a middleware layer, not a new model — it slots into the agent you already run (tokenolo wrap claude or tokenolo wrap codex). See Integrations.

Is it a new model?

No. tokenolo is middleware. It doesn't replace or change your model — it trims redundant filler from the input before that model sees it, then gets out of the way.

Do I have to change my workflow?

No rewiring. Same agents, same commands. tokenolo trims the input before it's sent, then steps aside.

Does my code go to tokenolo?

No. The proxy is local and the request goes to the model under your own key. Your files, tool output, and history are forwarded untouched, and tokenolo stores no prompt text, code, or history. See Security & privacy.

How much does it save?

Modestly — it removes filler, not context. The real value is a private, cache-safe trim with zero workflow change. More in Tokens & savings.

Do all plans have the same features?

Yes. Pricing is quota-based: every plan ships the same features and differs only by a daily wrap limit and requests-per-minute rate. See Plans & pricing.

How much does it cost?

Start free with no card. Paid plans are Pro $19/mo, Team $49/mo, and Business $99/mo, billed monthly. The full breakdown is on Plans & pricing.

How do I get started?

Sign up, install the CLI, wrap your agent, and work as usual — the Quickstart walks through it. Want to see it first? Book a demo.