Extract text/content from an image

POST

/v1/extract-generic

Runs generic OCR on an uploaded image and returns the generated files (html / markdown / json by default). Consumes 1 credit on success.

Request

Authorization

Bearer Token

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Body Params multipart/form-dataRequired

Responses

🟢200

application/json

Extraction succeeded

Bodyapplication/json

🟠401Unauthorized

🟠402InsufficientCredits

🟠422ValidationError

🔴500ExtractionError

Request Example

Shell

JavaScript

Java

Swift

curl --location '/v1/extract-generic' \
--header 'Authorization: Bearer <token>' \
--form 'file=@""' \
--form 'formats="html,markdown,json"'

Response Example

200 - Success

{
    "success": true,
    "data": {
        "files": {
            "html": "https://d36og1p9lvqwg0.cloudfront.net/ocr/results/abc123.html",
            "markdown": "https://d36og1p9lvqwg0.cloudfront.net/ocr/results/abc123.md",
            "json": "https://d36og1p9lvqwg0.cloudfront.net/ocr/results/abc123.json"
        },
        "confidence": 0.97
    },
    "credits_remaining": 41,
    "processing_time": 3.512
}

Modified at 2026-07-18 10:58:45

Extract tables from an image