tokeneff: An Open-Source LLM Cost Meter That Runs Locally

A developer released tokeneff, an open-source CLI that runs a local proxy on localhost:7860 to meter LLM API spending in real time, storing usage data in a local SQLite database. The tool distinguishes itself with month-end spend forecasting, separate CNY and USD tracking, and a BYOK mode that keeps keys and request metadata entirely local. It is installable via pip and supports a platform mode routing through the TokenEff gateway for wholesale pricing.

Most LLM dashboards show you the bill after the damage is done. You run a coding agent for an afternoon, ship a feature, and two days later your OpenAI dashboard says you spent $47. On what? Which model? Which request? You have no idea — and by then it's too late to do anything about it. This is the problem we kept hitting, so we built tokeneff https://github.com/zangxin75/token-efficiency — an open-source CLI that puts a real-time electricity meter on your LLM API spend. ⚡ tokeneff 电表 CNY 今日花费 ¥0.0284 本月累计 ¥0.2524 月终预测 ~¥0.93 100% 置信 累计节省 ¥0.0421 今日模型花费分布 deepseek-v4-flash ¥0.0192 15,797 tok glm-4-flash ¥0.0092 8,273 tok tokeneff runs a tiny local proxy on localhost:7860 . You point your LLM client's base url at it, and it: your client → tokeneff proxy localhost:7860 → LLM upstream ↓ local SQLite meter It's a transparent pipe. Your requests still go direct to the provider; tokeneff just reads the usage counts from the response and keeps a running tab. There are a few LLM cost trackers on GitHub already. Here's where tokeneff fits: | Feature | tokeneff | toktrack | tokencost | LLM-Cost-Guardian | |---|---|---|---|---| | Capture method | local proxy | reads CLI logs | manual / proxy | local proxy | | Real-time token count | ✅ | ❌ | ✅ | ✅ | | Month-end forecast | ✅ | ❌ | ❌ | ❌ | | Dual region / currency | ✅ | ❌ | ❌ | ❌ | | BYOK + platform dual-mode | ✅ | ❌ | ❌ | ❌ | | Budget alerts | ✅ | ❌ | ✅ | ✅ | Three things nobody else does: The killer feature. Based on your usage trend weighted: last 7 days × 70% + linear extrapolation × 30% , it predicts what you'll spend by month-end — with a confidence score. Seven days of data and it locks in. "At this rate, I'll hit $31 by the 31st" is the kind of number that actually changes behavior. If you're a Chinese developer using DeepSeek/GLM/Kimi, your spend is in CNY ¥. If you're using OpenAI/Claude, it's in USD $. Most tools mash these together into one meaningless number. tokeneff tracks them separately — CNY spend and USD spend are never mixed. BYOK mode is 100% free and local — your keys, your upstream, zero markup. But there's also a platform mode that routes through the TokenEff gateway one key, all models, wholesale pricing . The meter shows the savings: official price vs platform price, side by side. You switch when it makes sense, not when you're forced to. This matters more than people admit. A cost tracker that sends your request metadata to a cloud service to compute your bill is... not great. tokeneff: ~/.tokeneff/meter.db is a SQLite file you can rm anytime pip install tokeneff tokeneff setup pick provider, paste key tokeneff start starts the proxy on :7860 tokeneff stats see the meter tokeneff dashboard live TUI refreshes every 0.5s Point your client at http://localhost:7860/v1 and start building. Watch the meter while you work — not after. Ubuntu 22.04 gotcha: the default setuptools 59.6.0 is too old for PEP 621 and installs as UNKNOWN-0.0.0 . Run pip install --user --upgrade "setuptools =70" first. Yes, this is in the README too. Star ⭐ the repo https://github.com/zangxin75/token-efficiency if this solves a problem for you. Issues and PRs welcome — especially new provider additions. Building tokeneff as part of a broader open-source LLM gateway stack. BYOK meter first, gateway later. The meter is and will remain free + local.