I Built MLBox: A Browser Workbench That Shows How LLM Tokenizers Really Work Mohit Verma, a Class 10 student from Patna, India, built MLBox, an open-source, dependency-free browser workbench that compares seven real LLM tokenizers side by side, along with a neural-net playground, no-GPU project recipes, and an LLM price calculator. The tokenizer engine re-implements both BPE families in roughly 550 lines of JavaScript and matches the upstream Rust implementations token-for-token across 218,877 tokens on all seven models. Verma's demo shows the same Hindi phrase costing 5 tokens under GPT-4o's tokenizer versus 13 under cl100k, illustrating tokenization as a cost and context-window multiplier. Hi, I'm Mohit Verma, a Class 10 student from Patna, India, learning machine learning by building things. MLBox is my open-source project: a browser workbench for LLM tokenizers, training intuition, and API pricing. Four tools, one static page, zero dependencies — every number is measured in your own browser. Live demo: https://mohittt-vermaa.github.io/mlbox/ https://mohittt-vermaa.github.io/mlbox/ Code: https://github.com/mohittt-vermaa/mlbox https://github.com/mohittt-vermaa/mlbox Tokenizer lens — Paste any text and watch 7 real LLM tokenizers cut it up, token by token: counts, cost per million characters, a language cost matrix, a boundary diff between any two tokenizers, and a shareable link that freezes the whole comparison. Micro playground — A neural net with hand-written backprop training live on canvas. Watch gradient descent solve XOR. No-GPU recipes — 12 curated ML projects that genuinely finish on a laptop or a free Colab session, each with its one gotcha spelled out. LLM price bench — 13 current models from 5 providers, transcribed from each provider's own pricing page with source links, plus a workload calculator and a real-prompt cost estimator. Paste "नमस्ते दुनिया" "hello world" in Hindi, 13 characters and the tokenizers disagree: GPT-4o's tokenizer needs 5 tokens, Llama 3.1 needs 9, GPT-3.5/4's cl100k needs 13. Same two words, nearly 3x the bill depending on which tokenizer sits in front. Token choice is a cost multiplier and a context-window multiplier, and almost nobody looks at it. The tokenizer engine re-implements both BPE families in about 550 lines of dependency-free JavaScript, and the test suite checks it token-for-token against the upstream Rust implementations: 218,877 tokens, exact match on all seven models. There is also an Android app and a Windows desktop build in the releases, and everything runs offline with no API key and no backend — your text never leaves your machine. I kept reading claims about token costs from blog posts instead of measuring them. MLBox is my way of learning ML properly: build the tool, verify every number, and share it so the next student can measure things themselves. If it helps you, a star on GitHub means a lot: https://github.com/mohittt-vermaa/mlbox https://github.com/mohittt-vermaa/mlbox — Mohit Verma All my work: https://mohittt-vermaa.github.io https://mohittt-vermaa.github.io