[Integrations](https://spiral.ai/integrations) › [n8n](https://spiral.ai/integrations/n8n) › [Mistral document text extraction](https://spiral.ai/integrations/n8n/mistral-document-text-extraction)

# How to Use Mistral document text extraction in n8n

Mistral OCR 3 extracts text, tables, and embedded images from PDFs and images into page-based Markdown. Use it to turn scanned reports and complex tables into material an agent can search, compare, or analyze.

|  |  |
| --- | --- |
| Model | Mistral document text extraction |
| Available through | Mistral |
| Category | Data |
| Price | $0.0026 per page ($0.0039 with document or bounding-box annotations). |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Mistral document text extraction in n8n

- Each quarter, check Microsoft's investor relations publications and use Mistral document text extraction on any new earnings PDF to extract its financial tables.
- Each month, check Apple's investor relations publications and use Mistral document text extraction on new financial report PDFs to collect their product sales tables.
- Each year, use Mistral document text extraction on Berkshire Hathaway's newly published annual report PDF and compare its extracted section headings with the previous year's.
- Each week, check NVIDIA's investor relations publications and use Mistral document text extraction on newly posted earnings PDFs to extract the income statement.
- Each month, check for a revised PDF of the Mistral 7B paper at https://arxiv.org/pdf/2310.06825 and use Mistral document text extraction to compare its extracted tables with the previous copy.

## How to set up Mistral document text extraction in n8n

Pick the way that suits you. Each takes about two minutes.

### Use the Spiral skill

1. **Send n8n this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use Spiral's MCP server

1. **Create a key**: Create a key under API keys in the console.

2. **Add an MCP Client node**: In a workflow, add an MCP Client node (or, under an AI Agent node, an MCP Client Tool) and set:

```text
https://api.spiral.ai/mcp
```

3. **Pick a tool**: The node lists Spiral's tools. In an MCP Client node pick one, such as `run`, and give it its arguments:

```json
{
  "provider": "fal",
  "model": "fal-ai/flux/schnell",
  "input": { "prompt": "a lighthouse at dawn" },
  "wait": true
}
```

4. **Run Mistral document text extraction in a workflow step**: Give the step an instruction like the ones below and run it on your trigger or schedule. Spiral finds Mistral document text extraction, prices it and runs it each time the step fires.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Mistral document text extraction**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "mistral",
    "model": "mistral-ocr-3-0",
    "input": {
      "document": {
        "document_url": "<document_url>"
      }
    }
  }'
```

Then paste one of the prompts above: n8n finds Mistral document text extraction on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/n8n

## Mistral document text extraction tools and prices

- [Mistral OCR 3.0](https://spiral.ai/tools/mistral/mistral-ocr-3-0) (Mistral): $0.0026 per page ($0.0039 with document or bounding-box annotations).

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| pages |  | — | Specific pages to process. Accepts a list of integers or a string of comma-separated numbers and ranges (e.g. '0,1,2' or '0-5' or '0,2-4'). Page numbers start from 0. |
| image_limit |  | — | Max images to extract |
| table_format | markdown, html | — |  |
| extract_footer |  | false | Extract the page footer into the response's `footer` field and remove it from the markdown content |
| extract_header |  | false | Extract the page header into the response's `header` field and remove it from the markdown content |
| image_min_size |  | — | Minimum height and width of image to extract |

## What can you do with Mistral document text extraction in n8n?

Maintain a searchable record of newly published company reports by extracting each new PDF. A scheduled agent can compare the extracted text and tables with the previous edition after it obtains the documents.

### Search scanned business archives

Extract page text from archived company reports, then index it so staff can find passages without reading every scan.

### Compare annual report tables

Extract financial tables from successive public annual reports and compare rows while retaining their column headings.

### Prepare research papers for retrieval

Convert technical PDFs into page-based text for a research search tool, keeping extracted figures available alongside the text.

### Extract operational document fields

Turn authorized supplier invoices into structured records for a reviewer to check before entering them into accounting software.

### Compare manual revisions

Extract text and tables from two editions of a product manual, then identify changed specifications and instructions.

### Make historical publications searchable

Transcribe scanned institutional publications into searchable text, including handwritten annotations where present.

### Catalog figures in technical reports

Extract embedded figures and request captions to help readers locate relevant diagrams within a report collection.

## Overview

- [Mistral](https://spiral.ai/providers/mistral)
- [All n8n guides](https://spiral.ai/integrations/n8n)

## Mistral document text extraction in other agents

- [Amp](https://spiral.ai/integrations/amp/mistral-document-text-extraction)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/mistral-document-text-extraction)
- [Claude](https://spiral.ai/integrations/claude-desktop/mistral-document-text-extraction)
- [Claude Code](https://spiral.ai/integrations/claude-code/mistral-document-text-extraction)
- [Cline](https://spiral.ai/integrations/cline/mistral-document-text-extraction)
- [Codex](https://spiral.ai/integrations/codex/mistral-document-text-extraction)
- [Cursor](https://spiral.ai/integrations/cursor/mistral-document-text-extraction)
- [Devin](https://spiral.ai/integrations/devin/mistral-document-text-extraction)
- [dots](https://spiral.ai/integrations/dots/mistral-document-text-extraction)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/mistral-document-text-extraction)
- [Gemini](https://spiral.ai/integrations/gemini/mistral-document-text-extraction)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/mistral-document-text-extraction)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/mistral-document-text-extraction)
- [goose](https://spiral.ai/integrations/goose/mistral-document-text-extraction)
- [Grok](https://spiral.ai/integrations/grok/mistral-document-text-extraction)
- [Grok Build](https://spiral.ai/integrations/grok-build/mistral-document-text-extraction)
- [Hermes](https://spiral.ai/integrations/hermes/mistral-document-text-extraction)
- [Instinct](https://spiral.ai/integrations/instinct/mistral-document-text-extraction)
- [Manus](https://spiral.ai/integrations/manus/mistral-document-text-extraction)
- [Muse](https://spiral.ai/integrations/muse/mistral-document-text-extraction)
- [Muse Code](https://spiral.ai/integrations/muse-code/mistral-document-text-extraction)
- [Notion](https://spiral.ai/integrations/notion/mistral-document-text-extraction)
- [OpenClaw](https://spiral.ai/integrations/openclaw/mistral-document-text-extraction)
- [opencode](https://spiral.ai/integrations/opencode/mistral-document-text-extraction)
- [Perplexity](https://spiral.ai/integrations/perplexity/mistral-document-text-extraction)
- [Raycast](https://spiral.ai/integrations/raycast/mistral-document-text-extraction)
- [VS Code](https://spiral.ai/integrations/vscode/mistral-document-text-extraction)
- [Windsurf](https://spiral.ai/integrations/windsurf/mistral-document-text-extraction)
- [Zapier](https://spiral.ai/integrations/zapier/mistral-document-text-extraction)

## More n8n guides

- [Mistral document text and table extraction](https://spiral.ai/integrations/n8n/mistral-document-text-and-table-extraction)
- [Moondream 2 object bounding boxes](https://spiral.ai/integrations/n8n/moondream-2-object-bounding-boxes)
- [Mistral document OCR](https://spiral.ai/integrations/n8n/mistral-document-ocr)
- [Moondream 2 object coordinates](https://spiral.ai/integrations/n8n/moondream-2-object-coordinates)
- [Mistral OCR document extraction](https://spiral.ai/integrations/n8n/mistral-ocr-document-extraction)
- [SAM 3 image embedding](https://spiral.ai/integrations/n8n/sam-3-image-embedding)

## Questions about Mistral document text extraction in n8n

**Can n8n use Mistral document text extraction?**

Yes. Add Spiral to n8n as an MCP server, and n8n can find and run Mistral document text extraction like any built-in tool.

**How much does Mistral document text extraction cost in n8n?**

$0.0026 per page ($0.0039 with document or bounding-box annotations). You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your n8n plan is separate.

**Do I need a Mistral account to use Mistral document text extraction in n8n?**

You need no Mistral account. n8n uses one Spiral API key for every tool, and Spiral runs Mistral document text extraction on its own Mistral account.

**How long does it take to set up Mistral document text extraction in n8n?**

About two minutes: create a key, then add an MCP Client node, then pick a tool.

**Does n8n wait while Mistral document text extraction runs?**

Mistral document text extraction runs in the background. n8n starts the run, checks on it and gives you the json when it's ready.

**Where does the extracted information come from?**

It comes from the PDF or image submitted for processing. A report's contents therefore reflect that document's edition, including any outdated figures it contains.

**How large a document can Mistral OCR process?**

Mistral's chunking cookbook lists typical limits of approximately 50 MB and 1,000 pages per processing call. It recommends splitting larger documents into smaller parts and combining their results.

**Can OCR 3 extract tables with merged cells?**

Yes. Mistral documents support for merged cells, multi-row blocks, table headers, and column hierarchies.

**Does OCR 3 handle handwriting?**

Mistral describes support for cursive, mixed-content annotations, and handwriting layered over printed forms. These are supported document types, rather than a published guarantee of perfect transcription.

**Does OCR 3 return paragraph bounding boxes?**

Mistral's current documentation says paragraph-level block extraction requires OCR 4 or newer. Do not build an OCR 3 workflow that depends on those paragraph coordinates.

