> AI agents: this is one page from Mammoth Analytics documentation. The index of all pages as Markdown is https://mammoth.io/docs/llms.txt. Append `.md` to any docs URL, or send `Accept: text/markdown`, to get Markdown.

# PDF extraction page limits and using your own AI key

> How many PDF pages Mammoth extracts each month on each plan, the 2,000-page document limit, and how to read PDFs with your own OpenAI key instead.
>
> Applies to: 50 on Free, 200 on Starter, 500 on Team and 1,000 on Pro extracted pages a month with Mammoth's own key. Where: Data Library › your PDF › Extract Data › Review data import

Mammoth reads PDFs and images with AI. By default it uses Mammoth's own key, and the pages count toward your plan's monthly allowance of extracted pages; you can pick your workspace's own OpenAI key instead. The key is chosen at the top of the **Review data import** window (see [Extract tables from PDFs and images](https://mammoth.io/docs/learn/get-data-in/extract-from-pdfs/)).

## Choose which AI key reads the file

The top of **Review data import** says which key reads the document. Only OpenAI keys can read PDFs and images.

- With no key of your own: "Reading with Mammoth's own AI key." and an **Add your own key** link, which opens **Add External API Key** to paste an OpenAI key (see [Add your own AI provider key](https://mammoth.io/docs/learn/workspace/external-ai-keys/)).
- With OpenAI keys in the workspace: **Reading with** and a menu. Pick **Mammoth's own key** or one of your keys; each shows its model, such as **Model: gpt-4o**. **Add new key** adds another.

If you change the key after an extraction: "Key changed. Run the extraction again to see the results."

| Key | What counts against it |
| --- | --- |
| **Mammoth's own key** (the default) | Your plan's monthly allowance of extracted pages. Over it: "Monthly AI usage limit reached. Contact support to extend." On a plan without it: "This feature is not included in your current plan." |
| Your own OpenAI key | Your OpenAI account's credit and rate limits. Mammoth's page allowance isn't used. |

## Page limits for PDF extraction

| Limit | Value |
| --- | --- |
| Pages per document | Mammoth extracts up to the first 2,000 pages |
| Monthly extracted pages with Mammoth's own key | 50 on Free, 200 on Starter, 500 on Team and 1,000 on Pro. A run is charged only when it delivers tables |
| Long documents | If an extraction takes longer than Mammoth can wait, it says the extraction may still finish and to reopen the file in a few minutes |

See [Limits and quotas](https://mammoth.io/docs/learn/help/limits/).

## Troubleshoot page and quota errors

| Symptom | Cause | Fix |
| --- | --- | --- |
| Some pages were not extracted | Some pages had more data than your plan can extract | Use the **Upgrade your plan** link in the message |
| "Monthly AI usage limit reached. Contact support to extend." | Your monthly page allowance is used up | Wait for the next month, contact support, or use your own OpenAI key |
| "Your key has insufficient quota, no tables could be extracted. Please update your key or check your usage limits." | Your own AI key ran out of quota (the message says if some tables came first) | Update the key or check your limits with your AI provider, then extract again |

## Related

- [Extract tables from PDFs and images](https://mammoth.io/docs/learn/get-data-in/extract-from-pdfs/): the extraction flow and other errors.
- [Read new PDFs the same way](https://mammoth.io/docs/learn/get-data-in/read-pdfs-the-same-way/): each repeat read shows the AI pages it uses.
- [Limits and quotas](https://mammoth.io/docs/learn/help/limits/): every plan limit in one place.

---
Source: https://mammoth.io/docs/learn/get-data-in/pdf-extraction-limits.md · Updated: 2026-11-08