Developer API
Code Plagiarism
Detection API
Build plagiarism detection into your apps. Check code against 20+ billion sources.
const response = await fetch('https://codequiry.com/api/v1/check', {
method: 'POST',
headers: { 'apikey': 'YOUR_API_KEY' },
body: formData
});
// Check created!
AI DETECTION RESULTS API
Get AI Detection Results
Retrieve detailed AI-generated code detection results for an assignment. Identifies code that may have been generated by AI tools like ChatGPT, GitHub Copilot, or Claude, with per-file analysis and risk levels.
API Endpoint
POST https://codequiry.com/api/v1/ai-results
GET https://codequiry.com/api/v1/ai-results
Both
POST and GET are accepted and behave identically. Pass assignment_id as a body field (POST) or query string parameter (GET).
Authentication
Include your API key in the request header:
apikey: YOUR_API_KEY_HERERequest Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
assignment_id |
Integer | Required | The check/assignment ID to retrieve AI detection results for |
Success Response
HTTP Status: 200 OK
{
"success": true,
"assignment_id": 2810,
"assignment_name": "Python Assignment - Week 5",
"assignment_status": 4,
"statistics": {
"total_submissions": 25,
"submissions_with_ai_detection": 25,
"submissions_with_code_quality": 25,
"avg_ai_detection": 22.3,
"avg_code_quality": 78.4,
"high_ai_risk_count": 3,
"medium_ai_risk_count": 5,
"low_ai_risk_count": 17
},
"submissions": [
{
"submission_id": 45001,
"filename": "student1_solution",
"status": "Completed",
"status_id": 4,
"plagiarism_score": {
"local": 12.3,
"web": 40.0,
"total": 52.3
},
"matches": {
"local": 2,
"web": 5
},
"ai_detection": {
"total_files": 4,
"avg_ai_probability": 72.5,
"max_ai_probability": 85.2,
"min_ai_probability": 45.8,
"risk_level": "high",
"files": [
{
"id": 991,
"file_path": "main.py",
"ai_probability": 85.2,
"human_probability": 14.8,
"classification": "ai_generated",
"confidence": 0.92,
"summary": "Strong indicators of AI-generated code.",
"detailed_report": "...",
"created_at": "2024-09-15T12:30:00.000000Z"
}
]
},
"ai_code_quality": {
"total_files": 4,
"avg_score": 82.5,
"max_score": 90.0,
"min_score": 72.0,
"files": [
{
"id": 771,
"file_path": "main.py",
"score": 82.5,
"level": "good",
"total_lines": 120,
"comment_density": 0.18,
"entropy": 4.21,
"issues": "...",
"created_at": "2024-09-15T12:30:00.000000Z"
}
]
},
"file_size": 24576,
"created_at": "2024-09-15T12:25:00.000000Z",
"updated_at": "2024-09-15T12:30:00.000000Z"
}
]
}
Response Fields
- assignment_status — The assignment's numeric status ID (e.g.
4= Completed) - statistics — Aggregate AI detection and code-quality statistics for the entire assignment
- statistics.submissions_with_ai_detection — Count of submissions that have AI detection results
- statistics.submissions_with_code_quality — Count of submissions that have code-quality results
- statistics.avg_ai_detection — Average AI probability across all submissions (%)
- statistics.avg_code_quality — Average code-quality score across all submissions
- statistics.high_ai_risk_count — Submissions with avg AI probability >= 70%
- statistics.medium_ai_risk_count — Submissions with avg AI probability 45-69%
- statistics.low_ai_risk_count — Submissions with avg AI probability < 45%
- submissions[].status / status_id — Submission processing status (text and numeric ID)
- submissions[].plagiarism_score — Object with
local,web, andtotalsimilarity scores - submissions[].matches — Object with
localandwebmatch counts - submissions[].ai_detection — Per-submission AI detection breakdown (
nullwhen no AI results exist) - submissions[].ai_detection.avg_ai_probability / max_ai_probability / min_ai_probability — AI probability stats across the submission's files (%)
- submissions[].ai_detection.risk_level — Overall risk classification:
high,medium, orlow - submissions[].ai_detection.files[] — Per-file AI detection analysis
- files[].file_path — Path of the analyzed file
- files[].ai_probability / human_probability — Probability the file is AI- / human-written (0-100%)
- files[].classification — Model classification label
- files[].confidence — Confidence score of the AI detection model
- files[].summary / detailed_report — Narrative explanation of the detection result
- submissions[].ai_code_quality — Per-submission code-quality breakdown (
nullwhen no results exist) withtotal_files,avg_score,max_score,min_score, and per-filescore,level,total_lines,comment_density,entropy, andissues
No submissions yet? If the assignment has no submissions, the endpoint still returns
200 OK with "success": true, a "message": "No submissions found for this assignment", and an empty submissions array.
Understanding AI Risk Levels
High Risk (>= 70%)
Strong indicators of AI-generated code. The submission shows patterns highly consistent with AI output such as uniform formatting, templated structures, and characteristic comment styles.
Medium Risk (45-69%)
Some indicators of AI assistance. The code may have been partially generated or heavily influenced by AI tools. Manual review recommended.
Low Risk (< 45%)
Minimal AI indicators detected. The code appears to be primarily human-written with natural coding patterns and style variations.
Important: AI detection scores should be used as guidance, not as definitive proof. Always combine AI detection with human review and consider the context of the assignment before making academic integrity decisions.
Error Responses
401 Unauthorized
Invalid or missing API key.
422 Validation Error
Missing or invalid assignment_id (must be an integer >= 1).
404 Not Found
Assignment not found or does not belong to your account.
Code Examples
cURL
curl -X POST "https://codequiry.com/api/v1/ai-results" \
-H "apikey: YOUR_API_KEY_HERE" \
-d "assignment_id=2810"
JavaScript
const response = await fetch('https://codequiry.com/api/v1/ai-results', {
method: 'POST',
headers: {
'apikey': 'YOUR_API_KEY_HERE',
'Content-Type': 'application/json'
},
body: JSON.stringify({ assignment_id: 2810 })
});
const data = await response.json();
if (data.success) {
console.log(`AI Detection Stats:`);
console.log(` High risk: ${data.statistics.high_ai_risk_count}`);
console.log(` Medium risk: ${data.statistics.medium_ai_risk_count}`);
console.log(` Low risk: ${data.statistics.low_ai_risk_count}`);
// Flag high-risk submissions
const highRisk = data.submissions.filter(
s => s.ai_detection.risk_level === 'high'
);
highRisk.forEach(s => {
console.log(`\nFlagged: ${s.filename}`);
console.log(` AI Probability: ${s.ai_detection.avg_ai_probability}%`);
s.ai_detection.files.forEach(f => {
console.log(` ${f.filename}: ${f.ai_probability}% - ${f.indicators.join(', ')}`);
});
});
}
Python
import requests
response = requests.post(
'https://codequiry.com/api/v1/ai-results',
headers={'apikey': 'YOUR_API_KEY_HERE'},
data={'assignment_id': 2810}
)
data = response.json()
if data['success']:
stats = data['statistics']
print(f"Total submissions: {stats['total_submissions']}")
print(f"High AI risk: {stats['high_ai_risk_count']}")
print(f"Medium AI risk: {stats['medium_ai_risk_count']}")
print(f"Average AI detection: {stats['avg_ai_detection']}%")
# Process each submission
for sub in data['submissions']:
ai = sub['ai_detection']
if ai['risk_level'] in ('high', 'medium'):
print(f"\nFlagged: {sub['filename']} ({ai['risk_level']} risk)")
for f in ai['files']:
print(f" {f['filename']}: {f['ai_probability']}%")