Mistral OCR 4.1
mistral-ocr-4-1Extract text and tables from documents with Mistral OCR 4.1 through one Spiral API key. Extracts text, tables and images from PDFs and images into markdown with Mistral OCR 4.1, with optional structured fields. It runs in the background and returns structured JSON. Pay as you go, with no subscription.
Pricing
$0.0052 per page ($0.0065 with document or bounding-box annotations).
Limits
- Runs
- In the background
- Returns
- json
- Longest queue wait
- 1 hour
- Run deadline
- 30 minutes
- Longest run, end to end
- 225 minutes
- Largest inline input
- 1 MB
- Largest input file
- 2 GB
- Largest output
- 5 GB
Input
| Field | Kind | Default | Description |
|---|---|---|---|
document required | JSON | — | Document to run OCR on |
pages | JSON | — | 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 | number (whole) | — | Max images to extract |
table_format | one of markdown, html | — | |
extract_footer | true or false | false | Extract the page footer into the response's |
extract_header | true or false | false | Extract the page header into the response's |
image_min_size | number (whole) | — | Minimum height and width of image to extract |
include_blocks | true or false | true | Return paragraph-level bounding boxes for all content blocks in the response |
include_image_base64 | true or false | — | Include image URLs in response |
bbox_annotation_format | JSON | — | Structured output class for extracting useful information from each extracted bounding box / image from document. Only json_schema is valid for this field |
document_annotation_format | JSON | — | Structured output class for extracting useful information from the entire document. Only json_schema is valid for this field |
document_annotation_prompt | text | — | Optional prompt to guide the model in extracting structured output from the entire document. A document_annotation_format must be provided. |
confidence_scores_granularity | one of word, page, 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. |
Same request in code
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>"
}
}
}'Frequently asked questions
How much does Mistral OCR 4.1 cost?
$0.0052 per page ($0.0065 with document or bounding-box annotations). You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.
How do I use Mistral OCR 4.1 through an API?
Send `POST /v1/runs` with `"provider": "mistral"`, `"model": "mistral-ocr-4-1"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.
Do I need an account with Mistral to use Mistral OCR 4.1?
No. Spiral runs it on its own Mistral account and charges your Spiral balance.
Can my AI agent use Mistral OCR 4.1?
Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.