cd /news/large-language-models/i-built-mlbox-a-browser-workbench-th… · home › topics › large-language-models › article
[ARTICLE · art-173406] src=dev.to ↗ pub= topic=large-language-models verified=true sentiment=↑ positive

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.

key takeaway

The same 13-character Hindi phrase tokenizes to 5 tokens in GPT-4o, 9 in Llama 3.1 and 13 in cl100k, so tokenizer choice can nearly triple both cost and context usage for non-English text.

by read2 min views8 publishedNov 20, 2026

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 — Mohit Verma

All my work: https://mohittt-vermaa.github.io

── more in #large-language-models 4 stories · sorted by recency
── more on @mohit verma 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/i-built-mlbox-a-brow…] indexed:0 read:2min 2026-11-20 · —