I built AI Grammar Checker because I was tired of copy-pasting my writing between five different tools — Grammarly for grammar, Hemingway for readability, some word counter for stats.
What it does
Paste English text, hit check, and get back:
- Sentence-by-sentence grammar corrections with explanations
- Style polish — passive voice, weak adverbs, wordy phrases flagged
- Flesch readability score so you know if your text is actually readable
- Hemingway-style highlights — hard sentences, very hard sentences, adverb count
- CEFR level (A1–C2) for non-native speakers
- Tone detection — formal, casual, neutral
All client-side except the AI check call. No server stores your text.
The stack
HTML + vanilla JS + CSS
↓
DeepSeek API (OpenAI-compatible, $0.27/million tokens)
↓
Result rendered directly in the DOM
No React. No Next.js. No build step. Just app.js, style.css, and index.html.
Why DeepSeek over OpenAI
- Cost. DeepSeek is roughly 1/10th the price of GPT-4o for comparable grammar quality. At free tier usage levels, my API bill is under $2/month.
- Quality. Tested on a 50-sample set — DeepSeek caught 91% of errors vs GPT-4os 93%. The 2% gap is not worth 10x the cost.
- No content moderation false positives. OpenAI sometimes flags academic writing about medical or legal topics. DeepSeek just checks grammar.
What Id do differently
- Offline mode. Hemingway stats are local. Grammar needs the API. Want to bundle a small on-device model via WebLLM.
- Better mobile UX. Works on mobile but text area + results layout is not great on narrow screens.
- API key flow. Users bring their own DeepSeek key (5M free tokens for new users). Considering a shared-key free tier.
→ grammaraicheck.com — completely free, no signup.
Top comments (0)