MistralDocument to textAvailable now

mistral-ocr-4

Name: mistral-ocr-4
Brand: Mistral
Availability: InStock

mistral-ocr-4 is a document to text tool from Mistral that runs in the background and returns structured JSON. Pay as you go from $0.0052 per page, with one API key.

Try itfrom $0.0052 / page

Pricing

$0.0052 per page, or $0.0065 per page with document_annotation_format or bbox_annotation_format. Billed on pages, or the file's page count. The final charge comes from usage.

Limits

Runs: In the background
Returns: json
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

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 `footer` field and remove it from the markdown content
`extract_header`	true or false	false	Extract the page header into the response's `header` field and remove it from the markdown content
`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",
    "input": {
      "document": {}
    }
  }'