Image to text (OCR)

The image-to-text endpoint allows you to analyze an image and ask questions about its content via the WetroCloud API.
This endpoint supports two response formats to suit different use cases:

• Free Text Response: A natural language answer to your query.
• Structured Output Response: A structured JSON output (Coming Soon…).

Each response type has unique request and response formats, which are explained in detail on their respective pages.

​

Free Text Response

Free text response provides natural, conversational-style answers to your queries. It is ideal for general Q&A and scenarios where a narrative or contextualized explanation is needed. Unlike structured output, free text does not require additional parameters like json_schema and json_schema_rules.

​

Request Example

curl --request POST \
  --url https://api.wetrocloud.com/v1/image-to-text/ \
  --header 'Authorization: Token <api-key>' \
  --header 'Content-Type: application/json' \
  --data '{
    "image_url": "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTQBQcwHfud1w3RN25Wgys6Btt_Y-4mPrD2kg&s",
    "request_query": "What animal is this?"
  }'

​

Response Example: Free Text

{
    "response": "This is a dog, specifically a Labrador Retriever.",
    "tokens": 1594,
    "success": true
}