POST https://api.copyleaks.com/v2/writer-detector/{scanId}/check

Use Copyleaks AI Content Detection to differentiate between human-written and AI-written text.

This endpoint will receive submitted text to be checked. At the end of the processing stage, the result will be shown as classifications. Text classification is divided into sections. Each section may have a different classification.

Authentication Required

You need to login with a user and API key in order to access this method. Add this HTTP header to your request:

Authorization: Bearer < Your-Login-Token >

Request

Path Parameters

scanId string Required

A unique scan id provided by you. We recommend you use the same id in your database to represent the scan in the Copyleaks database. This will help you to debug incidents. Using the same ID for the same file will help you to avoid network problems that may lead to multiple scans for the same file. learn more about the criteria for creating a Scan ID.

>= 3 characters <= 36 characters

Match pattern: [a-z0-9] !@$^&-+%=_(){}<>';:/.",~|

Headers

Content-Type: application/json
Authorization: Bearer YOUR_LOGIN_TOKEN

Request Body

The request body is a JSON object containing the text to scan.

text string Required

A text string.

>= 255 characters <= 25000 characters

sandbox boolean default: "false"

Use sandbox mode to test your integration with the Copyleaks API for free.

language string

The language code of your content. The selected language should be on the Supported Languages list below. If the ‘language’ field is not supplied, our system will automatically detect the language of the content.

Language	Code
English	"en"
Spanish	"es"
French	"fr"
Portuguese	"pt"
German	"de"
Italian	"it"
Russian	"ru"
Polish	"pl"
Romanian	"ro"
Dutch	"nl"
Swedish	"sv"
Czech	"cs"
Norwegian	"no"
Korean	"ko"
Japanese	"ja"
Chinese (Simplified)	"zh-CN"
Chinese (Traditional)	"zh-TW"
Arabic	"ar"
Bengali	"bn"
Bulgarian	"bg"
Croatian	"hr"
Greek	"el"
Hebrew	"he"
Hindi	"hi"
Hungarian	"hu"
Serbian	"sr"
Thai	"th"
Turkish	"tr"
Ukrainian	"uk"
Vietnamese	"vi"

Example: "en"

explain boolean default: "false" Beta

Enable AI Logic feature for AI detection. Example:

{
  "text": "Your text here",
  "explain": true
}

For further information, please check the AI Logic for a detailed breakdown of its structure and usage, and for full AI Detection response please check the AI Detection Response.

sensitivity integer default: "2"

Control the behavior of the AI detection.

• Detecting content copied directly from an LLM, like ChatGPT or Gemini, without edits.
• Detecting content from an LLM with minor changes, like tense adjustments or added words.
• Detecting content from an LLM that has been heavily modified using tools or manual edits.

>= 1 <= 3

Responses

200

200 OK

The command was executed.

Response Schema

The response contains the following fields:

modelVersion string

The version of the AI detection model used (e.g., "v5").

results array

An array of classification results for different sections of the text.

classification integer

Classification result: 1 = Human, 2 = AI.

probability number

Confidence score for the classification (0-1).

matches array

Text segments that contributed to this classification with character and word positions.

summary object

Overall classification summary.

human number

Percentage of text classified as human-written (0-1).

ai number

Percentage of text classified as AI-generated (0-1).

scannedDocument object

Metadata about the scan.

scanId string

The unique identifier for this scan.

totalWords integer

Total number of words analyzed.

totalExcluded integer

Number of words excluded from analysis.

actualCredits integer

Credits actually consumed for this scan.

expectedCredits integer

Expected credits for this scan.

creationTime string

ISO 8601 timestamp when the scan was created.

explain object

AI Logic explanation data (only when explain=true).

patterns object

Detailed analysis patterns and statistics for AI detection reasoning.

statistics object

Statistical data including AI and human counts.

text object

Text position data for character and word analysis.

Example Response

A typical response from this endpoint:

Show full example (115 lines)

{
  "modelVersion": "v5",
  "results": [
    {
      "classification": 2,
      "probability": 1,
      "matches": [
        {
          "text": {
            "chars": {
              "starts": [
                0
              ],
              "lengths": [
                1509
              ]
            },
            "words": {
              "starts": [
                0
              ],
              "lengths": [
                221
              ]
            }
          }
        }
      ]
    }
  ],
  "summary": {
    "human": 0,
    "ai": 1
  },
  "scannedDocument": {
    "scanId": "check",
    "totalWords": 221,
    "totalExcluded": 0,
    "actualCredits": 1,
    "expectedCredits": 1,
    "creationTime": "2023-01-10T10:07:58.9459512Z"
  },
  "explain": {
    "patterns": {
      "statistics": {
        "aiCount": [
          15.9636,
          39.5495,
          84.7079,
          119.871,
          9.9233,
          185.667,
          14.4536,
          19.1995
        ],
        "humanCount": [
          0.8076,
          1.5076,
          3.8228,
          8.5071,
          0.3769,
          4.2536,
          0.3231,
          1.1845
        ]
      },
      "text": {
        "chars": {
          "starts": [
            31,
            55,
            303,
            909,
            961,
            987,
            1129,
            1775
          ],
          "lengths": [
            23,
            32,
            23,
            33,
            25,
            30,
            30,
            19
          ]
        },
        "words": {
          "starts": [
            5,
            9,
            45,
            135,
            144,
            148,
            169,
            257
          ],
          "lengths": [
            4,
            6,
            3,
            6,
            4,
            5,
            5,
            3
          ]
        }
      }
    }
  }
}

{
  "modelVersion": "v5",
  "results": [
    {
      "classification": 2,
      "probability": 1,
      "matches": [
        {
          "text": {
            "chars": {
              "starts": [
                0
              ],
              "lengths": [
                1509
// ... truncated

400

400 Bad Request

Bad request.

401

401 Unauthorized

Authorization has been denied for this request.

429

429 Too Many Requests

Too many requests have been sent. The request has been rejected.

Examples

HTTP

POST https://api.copyleaks.com/v2/writer-detector/my-scan-123/check
Content-Type: application/json
Authorization: Bearer YOUR_LOGIN_TOKEN

{
  "text": "Copyleaks is a comprehensive plagiarism detection platform that performs extensive searches across 60 trillion websites, 15,000+ academic journals, 20+ code data repositories, and 1M+ internal documents. Using AI-powered text analysis, easily scan documents, raw text, code, and URLs and instantly receive detailed reporting on the findings.",
  "sandbox": false,
  "explain": true,
  "sensitivity": 2
}

cURL

curl --request POST \
  --url https://api.copyleaks.com/v2/writer-detector/my-scan-123/check \
  --header 'Authorization: Bearer YOUR_LOGIN_TOKEN' \
  --header 'Content-Type: application/json' \
  --data '{
    "text": "Copyleaks is a comprehensive plagiarism detection platform that performs extensive searches across 60 trillion websites, 15,000+ academic journals, 20+ code data repositories, and 1M+ internal documents. Using AI-powered text analysis, easily scan documents, raw text, code, and URLs and instantly receive detailed reporting on the findings.",
    "sandbox": false,
    "explain": true,
    "sensitivity": 2
  }'

Python

import requests

# Sample text to analyze for writer detection
sample_text = """Copyleaks is a comprehensive plagiarism detection platform that performs extensive searches across 60 trillion websites, 15,000+ academic journals, 20+ code data repositories, and 1M+ internal documents. Using AI-powered text analysis, easily scan documents, raw text, code, and URLs and instantly receive detailed reporting on the findings."""

url = "https://api.copyleaks.com/v2/writer-detector/my-scan-123/check"
payload = {
    "text": sample_text,
    "sandbox": False,
    "explain": True,
    "sensitivity": 2
}
headers = {
    "Authorization": "Bearer YOUR_LOGIN_TOKEN",
    "Content-Type": "application/json",
    "Accept": "application/json"
}

response = requests.post(url, json=payload, headers=headers)
result = response.json()

print("Writer Detection Results:")
print(f"AI Score: {result.get('summary', {}).get('ai', 'N/A')}")
print(f"Human Score: {result.get('summary', {}).get('human', 'N/A')}")
print(response.json())

JavaScript

const { Copyleaks, CopyleaksNaturalLanguageSubmissionModel } = require('plagiarism-checker');

async function checkTextWriterDetection() {
    try {
        // Initialize Copyleaks
        const copyleaks = new Copyleaks();

        // Login to get the authentication token object.
        // Replace with your email and API key.
        const loginResult = await copyleaks.loginAsync('[email protected]', 'YOUR_API_KEY');

        const scanId = "my-scan-123";

        // The text to be checked
        const textToCheck = "Copyleaks is a comprehensive plagiarism detection platform that performs extensive searches across 60 trillion websites, 15,000+ academic journals, 20+ code data repositories, and 1M+ internal documents.";

        // Create a submission model
        const submission = new CopyleaksNaturalLanguageSubmissionModel(textToCheck);
        submission.sandbox = false;
        submission.explain = true;
        submission.sensitivity = 2;

        // Submit the text for analysis
        const response = await copyleaks.aiDetectionClient.submitNaturalTextAsync(loginResult, scanId, submission);
        console.log("Writer detection results:", response);

    } catch (error) {
        console.error("An error occurred:", error);
    }
}

checkTextWriterDetection();

Java

import classes.Copyleaks;
import models.submissions.aidetection.CopyleaksNaturalLanguageSubmissionModel;
import models.response.aidetection.AIDetectionResponse;

public class TextWriterDetectorExample {
    private static final String EMAIL_ADDRESS = "[email protected]";
    private static final String API_KEY = "00000000-0000-0000-0000-000000000000";

    public static void main(String[] args) {
        try {
            // Login to Copyleaks
            String authToken = Copyleaks.login(EMAIL_ADDRESS, API_KEY);
            System.out.println("Logged successfully!\nToken: " + authToken);

            // Sample text to analyze for writer detection
            String sampleText = "Copyleaks is a comprehensive plagiarism detection platform that performs " +
                "extensive searches across 60 trillion websites, 15,000+ academic journals, 20+ code data " +
                "repositories, and 1M+ internal documents. Using AI-powered text analysis, easily scan " +
                "documents, raw text, code, and URLs and instantly receive detailed reporting on the findings.";

            // Create natural language submission for writer detection
            String scanId = "my-scan-123";
            CopyleaksNaturalLanguageSubmissionModel textSubmission =
                new CopyleaksNaturalLanguageSubmissionModel(sampleText);

            // Configure submission parameters
            textSubmission.setSandbox(false);
            textSubmission.setExplain(true);
            textSubmission.setSensitivity(2);

            // Submit for writer detection analysis
            AIDetectionResponse result = Copyleaks.writerDetectorClient.submitNaturalLanguage(
                authToken,
                scanId,
                textSubmission
            );

            System.out.println("Writer detection submitted successfully!");
            System.out.println("AI Score: " + result.getSummary().getAi());
            System.out.println("Human Score: " + result.getSummary().getHuman());
            System.out.println("Full result: " + result);

        } catch (Exception e) {
            System.out.println("Failed: " + e.getMessage());
            e.printStackTrace();
        }
    }
}

Next Steps

Detect AI-Generated Text Learn how to use the AI Detection API to check if content was written by a human or generated by an AI.

AI Logic Understand how AI logic can help you interpret the results of AI text detection.

AI Detection Webhook Learn about the webhook that delivers AI detection results.