[Integrations](https://spiral.ai/integrations) › [Muse](https://spiral.ai/integrations/muse) › [Mistral document text and table extraction](https://spiral.ai/integrations/muse/mistral-document-text-and-table-extraction)

# How to Use Mistral document text and table extraction in Muse

Extract text, embedded images, and reconstructed tables from PDFs and images into Markdown. Use it to prepare reports, scans, and technical papers for search or analysis while retaining document structure.

|  |  |
| --- | --- |
| Model | Mistral document text and table 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 and table extraction in Muse

- Use Mistral document text and table extraction on https://arxiv.org/pdf/1706.03762 and explain the architecture using passages from the paper with page references.
- Use Mistral document text and table extraction on https://arxiv.org/pdf/1810.04805 and show me the extracted evaluation tables with their headings intact.
- Use Mistral document text and table extraction on https://arxiv.org/pdf/1512.03385 and make a reading outline from its section headings and key passages.
- Use Mistral document text and table extraction on https://arxiv.org/pdf/1706.03762 and list the extracted figures alongside their captions and source pages.
- Use Mistral document text and table extraction on https://arxiv.org/pdf/1810.04805 and extract the abstract and conclusion, then explain how their claims relate.

## How to set up Mistral document text and table extraction in Muse

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

### Use the Muse connector

1. **Create an API key**: Create one under API keys in the Spiral console.

2. **Send Muse this message**: Muse reads Spiral's skill and asks for an API key.

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

3. **Give Muse the key**: Paste the key when Muse asks for it, never in the chat itself.

### Use the Spiral skill

1. **Send Muse 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 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 and table 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-2512",
    "input": {
      "document": {
        "document_url": "<document_url>"
      }
    }
  }'
```

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

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

## Mistral document text and table extraction tools and prices

- [Mistral OCR 3 (2512)](https://spiral.ai/tools/mistral/mistral-ocr-2512) (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 and table extraction in Muse?

Turn a public technical paper into reading notes supported by extracted passages and tables. A chat assistant can use Mistral OCR text and images to explain the document and show the source material behind its answer.

### Make public reports searchable

Convert annual reports and agency publications into page-level Markdown for a searchable reference collection.

### Recover tables for analysis

Extract tables from public research papers and business reports, retaining merged headers before converting the results into analysis-ready rows.

### Build a technical reference assistant

Turn equipment manuals and technical PDFs into text and embedded images that an assistant can use to answer document questions.

### Compare report editions

Extract successive editions of a public report, then compare sections and tables to identify changes in the published material.

### Create structured document records

Use document annotations to collect selected headings, report identifiers, and other document details into a consistent JSON structure.

### Prepare research reading notes

Extract a paper's text, tables, and figures before producing notes that connect claims to their source pages.

## Overview

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

## Mistral document text and table extraction in other agents

- [Amp](https://spiral.ai/integrations/amp/mistral-document-text-and-table-extraction)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/mistral-document-text-and-table-extraction)
- [Claude](https://spiral.ai/integrations/claude-desktop/mistral-document-text-and-table-extraction)
- [Claude Code](https://spiral.ai/integrations/claude-code/mistral-document-text-and-table-extraction)
- [Cline](https://spiral.ai/integrations/cline/mistral-document-text-and-table-extraction)
- [Codex](https://spiral.ai/integrations/codex/mistral-document-text-and-table-extraction)
- [Cursor](https://spiral.ai/integrations/cursor/mistral-document-text-and-table-extraction)
- [Devin](https://spiral.ai/integrations/devin/mistral-document-text-and-table-extraction)
- [dots](https://spiral.ai/integrations/dots/mistral-document-text-and-table-extraction)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/mistral-document-text-and-table-extraction)
- [Gemini](https://spiral.ai/integrations/gemini/mistral-document-text-and-table-extraction)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/mistral-document-text-and-table-extraction)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/mistral-document-text-and-table-extraction)
- [goose](https://spiral.ai/integrations/goose/mistral-document-text-and-table-extraction)
- [Grok](https://spiral.ai/integrations/grok/mistral-document-text-and-table-extraction)
- [Grok Build](https://spiral.ai/integrations/grok-build/mistral-document-text-and-table-extraction)
- [Hermes](https://spiral.ai/integrations/hermes/mistral-document-text-and-table-extraction)
- [Instinct](https://spiral.ai/integrations/instinct/mistral-document-text-and-table-extraction)
- [Manus](https://spiral.ai/integrations/manus/mistral-document-text-and-table-extraction)
- [Muse Code](https://spiral.ai/integrations/muse-code/mistral-document-text-and-table-extraction)
- [n8n](https://spiral.ai/integrations/n8n/mistral-document-text-and-table-extraction)
- [Notion](https://spiral.ai/integrations/notion/mistral-document-text-and-table-extraction)
- [OpenClaw](https://spiral.ai/integrations/openclaw/mistral-document-text-and-table-extraction)
- [opencode](https://spiral.ai/integrations/opencode/mistral-document-text-and-table-extraction)
- [Perplexity](https://spiral.ai/integrations/perplexity/mistral-document-text-and-table-extraction)
- [Raycast](https://spiral.ai/integrations/raycast/mistral-document-text-and-table-extraction)
- [VS Code](https://spiral.ai/integrations/vscode/mistral-document-text-and-table-extraction)
- [Windsurf](https://spiral.ai/integrations/windsurf/mistral-document-text-and-table-extraction)
- [Zapier](https://spiral.ai/integrations/zapier/mistral-document-text-and-table-extraction)

## More Muse guides

- [Mistral document OCR](https://spiral.ai/integrations/muse/mistral-document-ocr)
- [Mistral document text extraction](https://spiral.ai/integrations/muse/mistral-document-text-extraction)
- [Mistral OCR document extraction](https://spiral.ai/integrations/muse/mistral-ocr-document-extraction)
- [Moondream 2 object bounding boxes](https://spiral.ai/integrations/muse/moondream-2-object-bounding-boxes)
- [Mistral OCR 4.1](https://spiral.ai/integrations/muse/mistral-ocr-4-1)
- [Moondream 2 object coordinates](https://spiral.ai/integrations/muse/moondream-2-object-coordinates)

## Questions about Mistral document text and table extraction in Muse

**Can Muse use Mistral document text and table extraction?**

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

**How much does Mistral document text and table extraction cost in Muse?**

$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 Muse plan is separate.

**Do I need a Mistral account to use Mistral document text and table extraction in Muse?**

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

**How long does it take to set up Mistral document text and table extraction in Muse?**

About two minutes: create an API key, then send Muse this message, then give Muse the key.

**Does Muse wait while Mistral document text and table extraction runs?**

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

**Which document formats can Mistral OCR process?**

Mistral lists PDF and seven image formats: PNG, JPG, JPEG, TIFF, BMP, GIF, and WEBP. The extracted content comes from the document you submit.

**How many pages can one OCR call process?**

Mistral's document chunking cookbook gives approximately 1,000 pages as the typical maximum per inference call. It recommends splitting documents that exceed the limits and combining the extracted results afterward.

**Can Mistral OCR preserve complex tables?**

OCR 3 reconstructs table headers, merged cells, multi-row blocks, and column hierarchies. Its HTML table output can represent structures that a simple Markdown table cannot.

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

No. Mistral documents paragraph-level block extraction as an OCR 4 or newer feature, so OCR 3 should not be used for paragraph-coordinate workflows.

**Does the reported 74% result mean 74% text accuracy?**

No. Mistral reports a 74% overall win rate against OCR 2 across forms, scanned documents, complex tables, and handwriting. That measures comparative wins, not the percentage of characters transcribed correctly.

