Skip to main content
POST
/
v3
/
ocr
Extract text from an image or PDF via a Layer gate
curl --request POST \
  --url https://api.verlon.ai/v3/ocr \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "gateId": "<string>",
  "data": {
    "documentUrl": "<string>",
    "imageUrl": "<string>",
    "base64": "<string>"
  },
  "model": "<string>",
  "metadata": "<unknown>",
  "endUserId": "<string>"
}
'
{
  "error": "<string>",
  "message": "<string>",
  "details": "<unknown>"
}

Documentation Index

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

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

Authorizations

​
Authorization
string
header
required

Layer API key (prefixed sk-). Generated from the dashboard under Settings → API Keys, or via layer key create in the CLI.

Body

application/json
​
gateId
string
required
​
data
object
required
​
model
string
​
metadata
any
​
endUserId
string

Response

OCR response with extracted text. Shape follows the underlying provider format selected by the gate.