ReplicateDocument to textComing soon

datalab-to/ocr

Name: datalab-to/ocr
Brand: Replicate

datalab-to/ocr is a document to text tool from Replicate that runs in the background and returns structured JSON. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Priced by usage

Pricing

$2.60 per 1,000 pages. Measured from the input file.

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
`file` required	text	—	Input file. Must be one of: .pdf, .doc, .docx, .ppt, .pptx, .png, .jpg, .jpeg, .webp
`max_pages`	number (whole) 1 to …	—	Maximum number of pages to process. Cannot be specified if page_range is set - these parameters are mutually exclusive
`visualize`	true or false	false	Draw red polygons on the input image(s) to visualize detected text regions and return the annotated images
`page_range`	text	—	Page range to parse, comma separated like 0,5-10,20. Example: '0,2-4' will process pages 0, 2, 3, and 4. Cannot be specified if max_pages is set - these parameters are mutually exclusive
`skip_cache`	true or false	false	Bypass the server-side cache and force re-processing. By default, identical requests are cached to save time and cost. Enable this to get fresh results
`return_pages`	true or false	false	Return detailed page information including text lines, bounding boxes, polygons, and character-level data. When disabled, only text and page_count will be returned

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": "replicate",
    "model": "datalab-to/ocr",
    "input": {
      "file": "<file>"
    }
  }'