OCR: text in an image
The text printed in an image (scan, screenshot, photo of a document). 1 live · 1 in the catalog.
| Provider | Price | Status |
|---|---|---|
| OCR: read the text in an image (Tesseract)SuperpowersSuperpowers documents | Free | Live |
Success rate and speed will show once a provider has 5 real calls in the last 30 days.
Run a comparison
Pick up to 6 live providers. Each one is charged at its own price; failures are free.
Questions
Which OCR text in an image API is cheapest?
Superpowers documents is free with any Superpowers account.
Is there a free OCR text in an image API?
Yes. Superpowers documents is free with any Superpowers account; you only need a key.
How do I call an OCR text in an image API from an AI agent?
Connect your agent once: paste the message from superpowers.tools/docs into Claude, ChatGPT or Codex. Then ask in your own words, and your agent picks this provider and runs it. You pay only when a call works, and new accounts get $5 free. Developers can call POST /v1/run with "tool": "superpowers.ocr" or use the MCP server.
For developersAPI call and the shared input and output format
Call it with one API key: POST /v1/run with "tool": "superpowers.ocr", or through the MCP server. Every provider takes the same input and returns the same output, and failed calls are not charged.
Input
{
"type": "object",
"additionalProperties": false,
"required": [
"image_url"
],
"properties": {
"image_url": {
"type": "string",
"format": "uri",
"maxLength": 2000,
"description": "Public link to a PNG, JPEG, TIFF, BMP, GIF or WebP image"
},
"languages": {
"type": "array",
"minItems": 1,
"maxItems": 3,
"uniqueItems": true,
"items": {
"type": "string",
"enum": [
"eng",
"por",
"spa"
]
},
"default": [
"eng"
],
"description": "Languages in the image: eng (English), por (Portuguese), spa (Spanish)"
}
}
}Normalized output
{
"text": "",
"confidence": 0,
"words": 0
}