[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [Mistral OCR 4.1](https://spiral.ai/integrations/instinct/mistral-ocr-4-1)

# How to Use Mistral OCR 4.1 in Instinct

Extract text, tables, and images from PDFs and images, with Markdown content and paragraph bounding boxes. Use it to turn public reports, research papers, or scanned documents into searchable text with locations you can check against the page.

|  |  |
| --- | --- |
| Model | Mistral OCR 4.1 |
| Available through | Mistral |
| Category | Data |
| Price | $0.0052 per page ($0.0065 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 OCR 4.1 in Instinct

- Each Monday, use Mistral document text extraction on newly published Berkshire Hathaway shareholder letters and report changes in the extracted section headings.
- Each month, check https://arxiv.org/pdf/1706.03762 for a revised document; when it changes, use Mistral document text extraction and compare the extracted tables with the previous version.
- Each quarter, use Mistral document text extraction on newly published Microsoft earnings release PDFs and collect the extracted financial tables with page references.
- Each Friday, use Mistral document text extraction on new NASA budget PDFs and list the program names and amounts found in their tables.
- Each month, use Mistral document text extraction on newly published Alphabet annual report PDFs and identify changes in the extracted risk factor headings.

## How to set up Mistral OCR 4.1 in Instinct

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

### Use the Spiral skill

1. **Send Instinct 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 an API key**: In the console, open API keys and create a key for Instinct. Copy it.

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

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

3. **Give Instinct the key**: When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

### 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 OCR 4.1**: 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-4-1",
    "input": {
      "document": {
        "document_url": "<document_url>"
      }
    }
  }'
```

Then paste one of the prompts above: Instinct finds Mistral OCR 4.1 on Spiral, shows the price and runs it.

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

## Mistral OCR 4.1 tools and prices

- [Mistral OCR 4.1](https://spiral.ai/tools/mistral/mistral-ocr-4-1) (Mistral): $0.0052 per page ($0.0065 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 OCR 4.1 in Instinct?

Keep a searchable archive of newly published company reports and research papers. On each scheduled run, Mistral can extract the supplied documents into text, tables, and page regions for comparison with earlier editions.

### Search public annual reports

Convert annual report PDFs into searchable text, keeping page locations beside passages about operating results and business risks.

### Extract research tables

Pull tables from research papers into a review worksheet, then compare the extracted cells with the original pages before analysis.

### Build a document viewer with source highlights

Use paragraph bounding boxes to highlight the source region when a reader selects extracted text.

### Compare editions of public reports

Extract each edition of a company report and compare passages or tables to identify changes for an analyst to review.

### Prepare public documents for retrieval

Turn PDF collections into Markdown passages with document and page references for a search or question-answering system.

### Create a figure review queue

Collect extracted figures from public research papers and keep them beside their source pages for captioning or editorial review.

### Structure public procurement documents

Extract document titles, submission deadlines, and requirements from public tender PDFs into a consistent review record.

## Overview

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

## Mistral OCR 4.1 in other agents

- [Amp](https://spiral.ai/integrations/amp/mistral-ocr-4-1)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/mistral-ocr-4-1)
- [Claude](https://spiral.ai/integrations/claude-desktop/mistral-ocr-4-1)
- [Claude Code](https://spiral.ai/integrations/claude-code/mistral-ocr-4-1)
- [Cline](https://spiral.ai/integrations/cline/mistral-ocr-4-1)
- [Codex](https://spiral.ai/integrations/codex/mistral-ocr-4-1)
- [Cursor](https://spiral.ai/integrations/cursor/mistral-ocr-4-1)
- [Devin](https://spiral.ai/integrations/devin/mistral-ocr-4-1)
- [dots](https://spiral.ai/integrations/dots/mistral-ocr-4-1)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/mistral-ocr-4-1)
- [Gemini](https://spiral.ai/integrations/gemini/mistral-ocr-4-1)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/mistral-ocr-4-1)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/mistral-ocr-4-1)
- [goose](https://spiral.ai/integrations/goose/mistral-ocr-4-1)
- [Grok](https://spiral.ai/integrations/grok/mistral-ocr-4-1)
- [Grok Build](https://spiral.ai/integrations/grok-build/mistral-ocr-4-1)
- [Hermes](https://spiral.ai/integrations/hermes/mistral-ocr-4-1)
- [Manus](https://spiral.ai/integrations/manus/mistral-ocr-4-1)
- [Muse](https://spiral.ai/integrations/muse/mistral-ocr-4-1)
- [Muse Code](https://spiral.ai/integrations/muse-code/mistral-ocr-4-1)
- [n8n](https://spiral.ai/integrations/n8n/mistral-ocr-4-1)
- [Notion](https://spiral.ai/integrations/notion/mistral-ocr-4-1)
- [OpenClaw](https://spiral.ai/integrations/openclaw/mistral-ocr-4-1)
- [opencode](https://spiral.ai/integrations/opencode/mistral-ocr-4-1)
- [Perplexity](https://spiral.ai/integrations/perplexity/mistral-ocr-4-1)
- [Raycast](https://spiral.ai/integrations/raycast/mistral-ocr-4-1)
- [VS Code](https://spiral.ai/integrations/vscode/mistral-ocr-4-1)
- [Windsurf](https://spiral.ai/integrations/windsurf/mistral-ocr-4-1)
- [Zapier](https://spiral.ai/integrations/zapier/mistral-ocr-4-1)

## More Instinct guides

- [GitHub user repositories](https://spiral.ai/integrations/instinct/github-user-repositories)
- [Mistral OCR document extraction](https://spiral.ai/integrations/instinct/mistral-ocr-document-extraction)
- [GitHub user pull requests](https://spiral.ai/integrations/instinct/github-user-pull-requests)
- [Mistral document OCR](https://spiral.ai/integrations/instinct/mistral-document-ocr)
- [GitHub user profile](https://spiral.ai/integrations/instinct/github-user-profile)
- [Mistral document text and table extraction](https://spiral.ai/integrations/instinct/mistral-document-text-and-table-extraction)

## Questions about Mistral OCR 4.1 in Instinct

**Can Instinct use Mistral OCR 4.1?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Mistral OCR 4.1 like any built-in tool.

**How much does Mistral OCR 4.1 cost in Instinct?**

$0.0052 per page ($0.0065 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 Instinct plan is separate.

**Do I need a Mistral account to use Mistral OCR 4.1 in Instinct?**

You need no Mistral account. Instinct uses one Spiral API key for every tool, and Spiral runs Mistral OCR 4.1 on its own Mistral account.

**How long does it take to set up Mistral OCR 4.1 in Instinct?**

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

**Does Instinct wait while Mistral OCR 4.1 runs?**

Mistral OCR 4.1 runs in the background. Instinct starts the run, checks on it and gives you the json when it's ready.

**Does Mistral OCR retrieve the latest version of a report?**

It extracts content from the PDF or image supplied for processing. The document determines the reporting period and freshness; processing an older report does not update its contents.

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

Mistral's chunking cookbook lists typical limits of approximately 50 MB and 1,000 pages. For larger documents, split the PDF into smaller sections before extraction.

**What language coverage does Mistral document?**

Mistral documents OCR 4 support for 170 languages across 10 language groups. That coverage statement does not promise identical recognition accuracy across languages.

**Can extracted text be located on the original page?**

OCR 4.1 supports paragraph bounding boxes and structural block labels. Those locations let a document viewer highlight the source region beside the extracted text.

**Does document annotation examine every extracted figure?**

Mistral's documented annotation workflow sends the extracted Markdown and the first eight extracted image bounding boxes to a vision model. A document annotation therefore does not include every image in a report containing more than eight extracted images.

