Skip to content
../products
● fastest in class

Coordinate Click Solver, solved in 5.0s.

Send an image + prompt, get back click coordinates. Works for any click-based captcha — Capzy's proprietary classifier handles arbitrary text prompts.

per 1,000$2.00
avg solve~5.0s
success99%+
throughput12/m
body: /9j/4AAQSkZJRgABAQ...…0.00s
POST/createTask type=CoordinatesTask
taskId tsk_o38hnjtb
POLL/getTaskResult status=processing
status ready
token 0xf79dcc846a753...
type: CoordinatesTask● running on production solvers

What is Coordinate Click?

A generic task for captchas that require clicking at specific points on an image. Send the image and a text description of what to click, and our AI returns the (x,y) coordinates. Useful for custom captchas ('click all fire hydrants'), Chinese character selection, and icon matching puzzles.

How It Works

1

Send Task

POST your CoordinatesTask with the target URL and sitekey to our API. We'll queue it instantly.

2

We Solve

Capzy's proprietary classifier returns the (x, y) coordinates that match your prompt. Useful for accessibility tooling and authorized image-analysis workflows.

3

Get Token

Poll getTaskResult — when status is 'ready', the solution contains the token to inject into the target page.

Quick Integration

solve.py
import requests, time

API = "https://api.capzy.ai"
KEY = "capzy_your_key_here"

# Step 1: Create task
task = requests.post(f"{API}/createTask", json={
    "clientKey": KEY,
    "task": {
        "type": "CoordinatesTask",
        "body": "/9j/4AAQSkZJRgABAQ...",
        "comment": "click all traffic lights"
    }
}).json()

task_id = task["taskId"]
print(f"Task created: {task_id}")

# Step 2: Poll for result
while True:
    result = requests.post(f"{API}/getTaskResult", json={
        "clientKey": KEY,
        "taskId": task_id
    }).json()

    if result["status"] == "ready":
        print("Solved!", result["solution"])
        break
    elif result["status"] == "failed":
        print("Failed:", result.get("errorDescription"))
        break

    time.sleep(1)

task parameters.

typetypestringreqyesCoordinatesTask
bodytypestringreqyesBase64-encoded image
commenttypestringreqyesText instruction describing what to click (e.g. 'click all traffic lights')

solution response.

coordinatestypearrayArray of {x, y} objects — the click points

Features

Capzy proprietary object detection + classification
Works with any text prompt
Returns multiple coordinates
< 3 second solve time

ProxyLess Task Type

CoordinatesTask

Frequently Asked Questions

start solving coordinate click.

$0.10 in free credits — no card. ~250 free solves to test before you spend.