Gemini OCR
Free image and PDF to text in your browser. Tables and formulas come back as clean Markdown.
About Gemini OCR & FAQ
How Gemini OCR works
Gemini OCR reads documents with Google's Gemini models. Drop in a PNG, JPEG or WebP image up to 20 MB or a PDF up to 50 MB and get the text back as Markdown, with tables kept as tables and formulas kept intact.
It runs in your browser with your own Gemini API key. Your file goes straight from your browser to Google's Gemini API; there is no Gemini OCR server in between.
- Models: Gemini 3.8 Flash, Gemini 4 Argon, Gemini 3.5 Flash-Lite, Gemini 3 Flash, Gemini 3.1 Pro.
- Handwriting mode for notes and filled-in forms.
- Choose a page range for long PDFs.
- Copy the result or download it as Markdown.
Is Gemini OCR free?
Yes. The app is free and needs no account. It runs on your own Gemini API key: Google offers a free tier with rate limits, and heavier use is billed by Google to your key. Some models, such as Gemini 4 Argon, need a paid key.
How do I get a Gemini API key?
Sign in to Google AI Studio, open the API keys page and create a key, then paste it into Settings here. It takes about a minute.
Where is my API key stored?
Only in this browser's local storage, lightly obfuscated. That is convenience storage, not encryption, so avoid shared computers. The key is sent only to Google's Gemini API.
Is Gemini OCR made by Google?
No. Gemini OCR is an independent project built on the public Gemini API. Gemini is a trademark of Google.