OCR Image to Text API
Tasks•Updated 5/4/2026
POST
https://solver.solverify.net/createTask
The Solverify OCR Image to Text API extracts text from a Base64-encoded image and returns the recognized value in solution.value. Use the OCR task for image-based text challenges and other supported image-to-text workflows.
Request Parameters
| Field | Required | Description |
|---|---|---|
clientKey | Yes | Your API key. |
base64 | Yes | Base64-encoded image content. Max 5,242,880 characters. |
Create Task Example
{
"clientKey": "YOUR_API_KEY",
"task": {
"type": "ocr",
"base64": "BASE64_ENCODED_IMAGE"
}
}
Create Response
{
"errorId": 0,
"taskId": "UUID"
}
Result Example
{
"errorId": 0,
"status": "completed",
"solution": {
"value": "EXTRACTED_TEXT"
},
"errorCode": null,
"errorDescription": null
}
Timeout
OCR tasks can run for up to about 30 seconds before timing out internally.
Next Steps
After creating an OCR task, poll the Get Task Result API with the returned taskId.