Image-to-Text (OCR)

Image-to-text models translate images into written output. The most common uses are image captioning and OCR, which describe scenes and extract text, respectively.

post

Endpoint for requesting image2text (OCR) inference

Authorizations
Header parameters
Acceptstring · enumRequiredPossible values:
Body
imagestring · binaryRequired

Image file to extract text from

modelstringRequired

The OCR model to use for text extraction

Example: tesseract-v5
languagestring | nullableOptional

Language code for OCR processing (optional)

Example: en
formatstring · enum | nullableOptional

Output format for extracted text

Example: textPossible values:
Responses
200

ID of the inference request.

application/json
post
POST /api/v1/client/img2txt HTTP/1.1
Host: api.deapi.ai
Authorization: Bearer JWT
Accept: application/json
Content-Type: multipart/form-data
Content-Length: 73

{
  "image": "binary",
  "model": "tesseract-v5",
  "language": "en",
  "format": "text"
}
{
  "data": {
    "request_id": 1
  }
}
post

Endpoint for calculating price for image2text (OCR) inference

Authorizations
Header parameters
Acceptstring · enumRequiredPossible values:
Body
image_urlstring · uriRequired

URL of image to extract text from

Example: https://example.com/image.jpg
modelstringRequired

The OCR model to use for text extraction

Example: tesseract-v5
languagestring | nullableOptional

Language code for OCR processing (optional)

Example: en
formatstring · enum | nullableOptional

Output format for extracted text

Example: textPossible values:
Responses
200

Calculated price for img2txt inference.

application/json
post
POST /api/v1/client/img2txt/price-calculation HTTP/1.1
Host: api.deapi.ai
Authorization: Bearer JWT
Accept: application/json
Content-Type: application/json
Content-Length: 100

{
  "image_url": "https://example.com/image.jpg",
  "model": "tesseract-v5",
  "language": "en",
  "format": "text"
}
{
  "data": {
    "price": 0.15
  }
}

Last updated