# Gemini OCR: can Gemini read images, scans and handwriting?

Yes, Gemini reads the text in photos and PDFs you upload to the Gemini app, up to 10 files per prompt and 100 MB per file[1]. The answer comes back as chat text, so you copy it out yourself. For a scan or a page of notes you want back as an editable Word file with its layout, LoreAI does OCR on every page.

## How to use Gemini for OCR

1. Open gemini.google.com or the Gemini app and add the photo or PDF to the prompt. In Chrome you can also drag an image in or paste one from a web page[1].
2. Ask for what you want, for example the full text of the page line by line, or the text as a table.
3. Copy the answer from the chat into your document.

Google says the Gemini app supports most file types, including documents, spreadsheets and photos[1]. That covers a phone photo of a whiteboard, a screenshot and a scanned PDF.

## What limits does Google list?

- **Files per prompt**: Up to 10, subject to availability[1]
- **File size**: Up to 100 MB for files other than video[1]
- **Long documents**: About 1,500 pages of text with the 1 million token context of the paid plans[1]
- **Upload rate**: Rolling limits on how much you can upload and analyze in a period of time, higher on paid plans[1]

Developers who call Gemini through the API get different limits. Google's API documentation lists PDFs up to 50 MB or 1,000 pages, reads each page as an image and counts each page as 258 tokens[2]. Its tips for scans are to rotate pages to the right orientation before uploading and to avoid blurry pages[2].

## Can Gemini read handwriting?

Gemini reads handwriting in a photo as part of the image, the same way it reads print. Google's help page for the Gemini app sets no separate rules for handwriting[1], so the usual photo advice applies: one page per shot, flat, straight on and in good light.

The difference shows on a stack of pages. A notebook of 30 pages means several prompts of 10 files each[1], and the text of each prompt comes back as one chat answer. LoreAI reads the whole PDF or set of photos in one upload and returns one Word file, page by page in the original order, with headings and lists as headings and lists. See [handwriting to text](https://www.loreai.org/handwriting-to-text) for notes, letters and diaries.

## Gemini and LoreAI side by side

*Checked on November 9, 2026, against Google's Gemini Apps Help and Gemini API docs*

| What you need | Gemini app | LoreAI |
| --- | --- | --- |
| File types | Most file types, photos and documents included[1] | PDF, JPG, PNG and HEIC |
| Size | 100 MB per file[1] | Free 3 MB, Basic 10 MB, Pro 25 MB |
| Files at once | Up to 10 per prompt[1] | One PDF of up to 100 pages on Pro |
| Scanned pages | Read as part of the file[1] | Every page read with OCR, in order |
| Photos | Uploaded or pasted into the prompt[1] | Uploaded directly, HEIC included |
| What you get | An answer in the chat | An editable Word file (.docx) with headings, lists and tables |
| Translation | Ask in the prompt | Into 105 languages in the same step |
| Price | Free, with higher limits on Google AI Pro and Ultra[1] | First document free, then Basic at $12.99 a month |

## When to use Gemini, and when a document OCR

- Use Gemini to ask about a photo: what a sign says, what a receipt totals, what a paragraph of notes means.
- Use Gemini for a summary of a scan, not the scan itself.
- Use LoreAI when you need the document back as a document: every line, the tables as tables, ready to edit in Word.
- Use LoreAI for a whole notebook or a long scan in one upload, or when the page also needs translating.

For a single photo or screenshot, the free [image to text](https://www.loreai.org/image-to-text) tool gives you the text and a Word download with no account. Compare the other assistants in [ChatGPT OCR](https://www.loreai.org/compare/chatgpt-ocr) and [Mistral OCR](https://www.loreai.org/compare/mistral-ocr).

## Questions people ask

### Can Gemini read text from an image?

Yes. Upload the photo to the Gemini app and ask for the text. Up to 10 files fit in one prompt[1].

### Can Gemini read handwriting?

It reads handwriting as part of the image. Clear, flat photos of one page each give it the best start. LoreAI reads handwritten pages into a Word file in one upload.

### Is Gemini OCR free?

Uploading files works on the free Gemini app, with rolling limits that are higher on Google AI Pro and Ultra[1].

### How many PDF pages can Gemini read?

Through the API, PDFs up to 1,000 pages or 50 MB[2]. In the app, files up to 100 MB[1].

## Sources

1. [Gemini Apps Help: Upload & analyze files in Gemini Apps](https://support.google.com/gemini/answer/14903178?hl=en), accessed November 9, 2026
2. [Gemini API: Document understanding](https://aistudio.google.com/docs/document-processing), accessed November 9, 2026

By Matt Mountain · Updated November 9, 2026