TokenScope
Real-time, privacy-first monitoring of your LLM API usage
TokenScope launched on May 25, 2026 with 1 votes.
What it does
TokenScope is a lightweight browser extension that quietly watches the LLM API calls made by any tab - ChatGPT, Claude, Gemini, or any OpenAI-compatible endpoint - and shows you in real time exactly how many tokens went in and out. Zero config. No account needed. 100% local - nothing ever leaves your browser. Works with ChatGPT, Claude, Gemini, OpenRouter, DeepSeek, and any custom gateway.
Contribute to vvvvking/tokenscope development by creating an account on GitHub.
TokenScope is a lightweight Chrome / Edge extension that quietly watches the LLM API calls made by any tab you're on — ChatGPT, Claude.ai, Gemini, Poe, Open WebUI, your own playground, anything that speaks the OpenAI / Anthropic / Gemini protocol — and shows you in real time exactly how many tokens went in and out, for which model, on which host. Nothing ever leaves your browser. No account. No telemetry. No built-in price tables that go stale. You type your own rates if you want a cost column. git clone https://github.com/YOUR-USERNAME/tokenscope cd tokenscope npm install npm run icons # generate PNG icons from SVG source Then open chrome://extensions → enable Developer mode → Load…from github.com
Does a similar job
all alternatives →
LLM SEO Monitor2025 · llmseomonitor.com · ▲526Monitor what ChatGPT, Google Gemini and Claude recommend
A MitM proxy to see what your LLM tools are sendingJan 2026 · github.com · ▲218I built this out of curiosity about what Claude Code was actually sending to the API. Turns out, watching your tokens tick up in real-time is oddly satisfying. Sherlock sits between your LLM tools and the API, showing you every request with a live dashboard, and auto-saved copies of every prompt as markdown and json.
- ATA tool to benchmark LLM APIs (OpenAI, Claude, local/self-hosted)2025 · llmapitest.com · ▲55
I recently built a small open-source tool to benchmark different LLM API endpoints — including OpenAI, Claude, and self-hosted models (like llama.cpp). It runs a configurable number of test requests and reports two key metrics: • First-token latency (ms): How long it takes for the first token to appear • Output speed (tokens/sec): Overall output fluency Demo: https://llmapitest.com/ Code: https://github.com/qjr87/llm-api-test The goal is to provide a simple, visual, and reproducible way to evaluate performance across different LLM providers, including…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Product Hunt launch ↗
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com