Tuteliq provides 21 specialized endpoints across safety, fraud, extended safety, analysis, and multi-endpoint detection. Each endpoint returns structured JSON responses with age-calibrated severity scoring.
Base URL
Request Format
All endpoints accept JSON requests. Most text-based endpoints use the following common structure:
Field
Type
Required
Description
text
string
Yes
The content to analyze
context
object
No
Additional context (type, age, platform)
Safety
Core detection endpoints for all nine KOSA harm categories. Supports text, voice, and image input with age-calibrated severity scoring.
Bullying Detection
Detect bullying, harassment, and intimidation in text
Grooming Detection
Detect grooming patterns in conversations
Unsafe Content
Detect KOSA-aligned harm signals in text
Voice Analysis
Analyze voice/audio for safety concerns with transcription
Image Analysis
Analyze image for visual and textual safety concerns
Video Analysis
Analyze video for visual safety concerns across extracted frames
Document Analysis
Upload PDFs for multi-endpoint safety analysis with per-page detection
Emotional Distress (Early Warning)
Detect pre-vulnerability emotional distress signals before exploitation begins
TFGBV Detection
Detect technology-facilitated gender-based violence with amplifier and intersectionality assessment
Fraud
Financial and social fraud detection, social engineering, app fraud, romance scams, and money mule recruitment. Identifies tactics targeting minors and vulnerable users with evidence-based scoring.
Social Engineering
Detect social engineering tactics in text
App Fraud Detection
Detect app fraud and financial scam patterns
Romance Scam
Detect romance scam indicators in conversation
Mule Recruitment
Detect money mule recruitment attempts
Safety Extended
Extended safety detection, gambling harm, coercive control, vulnerability exploitation with cross-endpoint modifiers, and radicalisation. Requires Build tier or above.
Gambling Harm
Detect gambling harm indicators
Coercive Control
Detect coercive control patterns
Vulnerability Exploitation
Detect exploitation of vulnerable individuals
Radicalisation
Detect radicalisation and extremism indicators
Analysis & Guidance
Emotional analysis, action plans, incident reporting, and self-harm detection for comprehensive safeguarding workflows.
Action Guidance
Get age-appropriate intervention recommendations
Incident Reports
Generate structured reports for safeguarding teams
Self-Harm Detection
Identify self-harm and suicidal ideation signals
Analyse
Multi-endpoint analysis. Fan-out a single text to up to 10 detection endpoints in parallel with aggregated results, vulnerability modifier support, and per-endpoint breakdowns.
Multi Analysis
Fan-out analysis across multiple detection endpoints
Endpoint Availability by Plan
Free (development)
- Safety (text only)
- Basic Analysis
Build
- All Safety endpoints
- Fraud Detection
Assure, Enterprise
- All endpoints
- Higher rate limits
- Priority latency