Spiral gives your agent every tool with one account. Browse the tools →

Notion · DataReleased 2025-12-18

How to Use Mistral document text and table extraction in Notion

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.

Prompts to try with Mistral document text and table extraction in Notion

Copy an example into Notion, or ask in your own words.

Each Monday, use Mistral document text and table extraction on https://arxiv.org/pdf/1706.03762 if the PDF has changed, then report changes in its extracted text.

Mistral document text and table extractionNotion
Try asking
  • Each month, use Mistral document text and table extraction on https://arxiv.org/pdf/1810.04805 if a new PDF revision is available, then compare its tables with the previous extraction.

  • Every Friday, use Mistral document text and table extraction on https://arxiv.org/pdf/1512.03385 if the PDF has changed, then list added or removed section headings.

  • At the start of each month, use Mistral document text and table extraction on any changed PDFs in my reading collection, beginning with https://arxiv.org/pdf/1706.03762, and produce page-referenced reading notes.

  • Each Monday, check https://arxiv.org/pdf/1810.04805 for a revised PDF and use Mistral document text and table extraction when it changes; report any differences in the extracted abstract and conclusion.

How to set up Mistral document text and table extraction in Notion

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

Use the Spiral skill

  1. Send Notion 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. Allow custom MCP servers

    A workspace owner opens Settings › Connections, then the Manage tab, and turns on Enable custom MCP servers. Where members may install only approved connections, also add Spiral under Approved connections › Add approved connection › Custom MCP server with the URL below.

  2. Add Spiral to a custom agent

    Open the custom agent (or create one), then Settings › Tools & Access › Add connection › Custom MCP server. Paste this URL, name it Spiral, keep OAuth and click Connect.

    https://api.spiral.ai/mcp
  3. Sign in to Spiral and approve

    Spiral opens: sign in, pick the organization and click Authorize. No API key. Spiral gives the connection its own key; Notion never sees it, and you can remove it under Settings › Connected apps in the console.

  4. Run Mistral document text and table 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 and table 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.

    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.

    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: Notion finds Mistral document text and table extraction on Spiral, shows the price and runs it.

Mistral document text and table extraction providers and prices

Spiral runs Mistral document text and table extraction through Mistral. Open a card for today's price, with every fee included.

MistralData
Mistral OCR 3 (2512)
mistral-ocr-2512

Settings you can ask for

Mistral document text and table extraction works from your document annotation prompt. Ask Notion for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Image limita whole number

Max images to extract

Table formatmarkdown or html
Extract footeron or offoff

Extract the page footer into the response's footer field and remove it from the markdown content

Extract headeron or offoff

Extract the page header into the response's header field and remove it from the markdown content

Image min sizea whole number

Minimum height and width of image to extract

Include blockson or offon

Return paragraph-level bounding boxes for all content blocks in the response

Include image base64on or off

Include image URLs in response

Confidence scores granularityword, page, or block

Granularity for confidence scores: 'page' (aggregate only), 'word' (per-word scores), or 'block' (per-block scores). Defaults to None (no confidence scores) to keep response payload small.

Every API field of Mistral OCR 3 (2512) is on its tool page: open its card above.

What can you do with Mistral document text and table extraction in Notion?

Keep a public PDF reading collection current by extracting newly published or revised documents on a schedule. An always-on agent can compare Mistral OCR text and tables across document editions and report changes in the source material.

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.

Questions about Mistral document text and table extraction in Notion

Can Notion use Mistral document text and table extraction?

Yes. Add Spiral to Notion as an MCP server, and Notion 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 Notion?

$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 Notion plan is separate.

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

No. Spiral runs Mistral document text and table extraction on its own Mistral account. You sign in to Spiral once and never paste a key.

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

About two minutes: allow custom MCP servers, then add Spiral to a custom agent, then sign in to Spiral and approve.

Does Notion wait while Mistral document text and table extraction runs?

Mistral document text and table extraction runs in the background. Notion 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.

Get started

Start using Mistral document text and table extraction in Notion

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Notion:

Set up Notion

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options