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

Grok · DataReleased 2025-12-18

How to Use Mistral document OCR in Grok

Mistral document OCR extracts text, tables, and embedded images from PDFs and images, with optional structured JSON annotations. Use it to turn reports and scanned documents into content an agent can search, compare, or analyze.

Prompts to try with Mistral document OCR in Grok

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

Use Mistral document OCR on Apple's 2024 annual report PDF, extract its consolidated statements of operations, and explain the table's rows and year headings.

Mistral document OCRGrok
Try asking
  • Use Mistral document OCR on https://arxiv.org/pdf/2310.06825 and summarize the Mistral 7B paper's methods from the extracted text.

  • Use Mistral document OCR on https://arxiv.org/pdf/1706.03762 and show me the extracted results tables before explaining them.

  • Use Mistral document OCR on https://upload.wikimedia.org/wikipedia/foundation/f/f6/WMF_Mid-Year-Financials_08-09-FINAL.pdf and turn its financial tables into a readable comparison.

  • Use Mistral document OCR on the first eight pages of Microsoft's 2024 annual report PDF and return its title, reporting period, and summary as structured data.

How to set up Mistral document OCR in Grok

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

Use the Grok connector

  1. Add a custom connector

    In Grok open Settings › Connect Apps, then Add a custom connector. Name it Spiral, paste this URL, leave Headers empty and click Add MCP.

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

    Grok opens Spiral: sign in, pick the organization and click Authorize. Spiral gives the connection its own API key; Grok never sees it, and you can remove the connection under Settings › Connected apps.

  3. Check that it is connected

    Connect Apps › Custom shows Spiral as Connected. It works in every Grok chat and Grok bot.

Use the Spiral skill

  1. Send Grok 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.

    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 OCR

    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-3",
        "input": {
          "document": {
            "document_url": "<document_url>"
          }
        }
      }'

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

Mistral document OCR providers and prices

Spiral runs Mistral document OCR through Mistral. Open a card for today's price, with every fee included.

MistralData
Mistral OCR 3
mistral-ocr-3

Settings you can ask for

Mistral document OCR works from your document annotation prompt. Ask Grok 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 is on its tool page: open its card above.

What can you do with Mistral document OCR in Grok?

Get readable text and usable tables from a public report PDF. A chat app can use the extracted content to explain a financial statement or summarize a research paper's methods.

Make annual reports searchable

Extract report text into Markdown for a company research index, then use it to find business segments, risks, and accounting notes.

Recover financial tables

Extract tables from public company reports for spreadsheet analysis. Preserve merged headers so year labels stay associated with the right figures.

Prepare research papers for analysis

Turn paper PDFs into extracted text and images that an agent can use to summarize methods, compare results, and inspect figures.

Compare public document revisions

Extract two editions of a government report or business publication, then compare the text and tables to identify changes.

Build a report metadata catalog

Use structured annotations to collect document titles, reporting periods, and summaries in a consistent JSON structure. Process long reports in sections of up to eight pages.

Describe figures for document search

Annotate extracted charts and figures with descriptions that help users find the relevant visual inside a collection of public reports.

Questions about Mistral document OCR in Grok

Can Grok use Mistral document OCR?

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

How much does Mistral document OCR cost in Grok?

$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 Grok plan is separate.

Do I need a Mistral account to use Mistral document OCR in Grok?

No. Spiral runs Mistral document OCR 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 OCR in Grok?

About two minutes: add a custom connector, then sign in to Spiral and approve, then check that it is connected.

Does Grok wait while Mistral document OCR runs?

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

Where does the extracted information come from, and how current is it?

Mistral extracts content from the PDF or image supplied for processing. Its information reflects that document, so processing an older annual report gives you that report's contents.

Can Mistral preserve complex tables?

OCR 3 supports reconstructed tables with merged cells, multi-row blocks, and hierarchical column headers. HTML output can represent cells spanning multiple rows or columns.

How much of a document can structured annotations cover?

Mistral's cookbook documents an eight-page limit for document annotations and recommends splitting longer documents. The annotation stage receives OCR text plus the first eight extracted image bounding boxes.

Does the reported 74% benchmark mean 74% transcription accuracy?

No. Mistral reports a 74% overall win rate against OCR 2 across forms, scans, complex tables, and handwriting; that measures comparative wins rather than the percentage of characters transcribed correctly.

Does OCR 3 return paragraph bounding boxes?

Paragraph-level block extraction requires OCR 4 or newer. Mistral says older models accept the option but return an empty array, so OCR 3 should not be used when paragraph coordinates are required.

Get started

Start using Mistral document OCR in Grok

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

Paste this into Grok:

Set up Grok

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