Vision Engine

WARNING

Create the task with the createTask.

This interface does not need to obtain the results separately, will directly return the image recognition results!

The task type field is as follows

VisionEngine

Create Task

Create the task with the createTask.

Task Object Structure

Note that this type of task returns the task execution result directly after createTask, rather than getting it asynchronously through getTaskResult.

Properties	Type	Required	Description
type	String	Required	VisionEngine
module	String	Required	All supported models are shown in the table below
websiteURL	String	Optional	Page source url to improve accuracy
image	String	Required	base64 encoded content of the image (no newlines, no data:image/***;charset=utf-8;base64,)
imageBackground	String	Required	base64 encoded content of the background image (no newlines, no data:image/***;charset=utf-8;base64,)
question	String	Optional	space_detection requires

SUPPORT IMG TYPES

module	Captcha Example	image	imageBackground
slider_1
rotate_1
space_detection

Example Request

Example request using slider module

POST https://api.capsolver.com/createTask
Host: api.capsolver.com
Content-Type: application/json

{
  "clientKey": "YOUR_API_KEY",
  "task": {
    "type": "VisionEngine",
    "module": "slider_1",
    "image": "/9j/4AAQSkZJRgABA......",
    "imageBackground": "/9j/4AAQSkZJRgABA......",
    "websiteURL": "https://xxxx.com"
  }
}

Example Response using slider module

{
  "errorId": 0,
  "errorCode": "",
  "errorDescription": "",
  "status": "ready",
  "solution": {
     "distance": 213,  
  },
  "taskId": "..."
}

Example request using rotate module

POST https://api.capsolver.com/createTask
Host: api.capsolver.com
Content-Type: application/json

{
  "clientKey": "YOUR_API_KEY",
  "task": {
    "type": "VisionEngine",
    "module": "rotate_1",
    "image": "/9j/4AAQSkZJRgABA......",
    "imageBackground": "/9j/4AAQSkZJRgABA......",
    "websiteURL": "https://xxxx.com"
  }
}

Example Response using rotate module

{
  "errorId": 0,
  "errorCode": "",
  "errorDescription": "",
  "status": "ready",
  "solution": {
     "angle": 154,   
  },
  "taskId": "..."
}

Example request using space_detection module

POST https://api.capsolver.com/createTask
Host: api.capsolver.com
Content-Type: application/json

{
  "clientKey": "YOUR_API_KEY",
  "task": {
    "type": "VisionEngine",
    "module": "space_detection",
    "image": "/9j/4AAQSkZJRgABA......",
    "question": "Please click on the unique object",
    "websiteURL": "https://xxxx.com"
  }
}

Example Response using space_detection module

{
  "errorId": 0,
  "errorCode": "",
  "errorDescription": "",
  "status": "ready",
  "solution": {
     "box": [163.5, 107.5] 
  },
  "taskId": "..."
}

Use SDK Request

# pip install --upgrade capsolver
# export CAPSOLVER_API_KEY='...'
 
import capsolver
 
# capsolver.api_key = "..."
 
img_path = os.path.join(Path(__file__).resolve().parent, "queue-it.jpg")
with open(img_path, 'rb') as f:
    solution = capsolver.solve({
        "type": "VisionEngine",
        "module": "slider_1",
        "image": "/9j/4AAQSkZJRgABA......",
        "imageBackground": "/9j/4AAQSkZJRgABA......"
    })
    print(solution)

AWS WAF hCaptcha