Skip to main content
POST
/
api
/
v2
/
images
/
ocr
/
price
cURL
curl --request POST \
  --url https://api.deapi.ai/api/v2/images/ocr/price \
  --header 'Accept: <accept>' \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'image=<string>' \
  --form model=Nanonets_Ocr_S_F16 \
  --form language=en \
  --form format=text \
  --form 0.image='@example-file'
{
  "data": {
    "price": 0.15
  }
}

Documentation Index

Fetch the complete documentation index at: https://docs.deapi.ai/llms.txt

Use this file to discover all available pages before exploring further.

Estimate the cost of an OCR job before submitting it.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Headers

​
Accept
enum<string>
default:application/json
required
Available options:
application/json

Body

multipart/form-data

Image to text conversion parameters

​
image
file
required

Image file to extract text from. Supported formats: JPG, JPEG, PNG, GIF, BMP, WebP. Maximum file size: 10 MB.

​
model
string
required

The OCR model to use for text extraction. Available models can be retrieved via the GET /api/v1/client/models endpoint.

Example:

"Nanonets_Ocr_S_F16"

​
language
string | null

Language code for OCR processing (optional)

Example:

"en"

​
format
enum<string> | null

Output format for extracted text

Available options:
text,
json
Example:

"text"

Response

Calculated price for img2txt inference.

​
data
object