AI Observability Live Demo

Complete LLM Monitoring, Cost Optimization & Safety Suite

140+ Endpoints 35+ Controllers 6+ AI Providers Real-time WebSocket
LIVE METRICS
$0.00
Total Cost (24h)
LIVE
REQUESTS
0
Last 24 Hours
TOKENS
0
Processed
BUDGET STATUS
$1000.00
Spent: $0.00
📊 RECENT TRANSACTIONS 0 ▼
Click "Refresh" to see recent transactions
📝 Prompt Input
Groq ⚡ 5x faster than Google
⚡ Llama 3.1 8B
Groq · 58ms · ~$0.00003
🏆 Fastest
🦙 Llama 3.3 70B
Groq · 386ms · ~$0.00003
🧠 Best Reasoning
🤖 GPT-OSS 120B
Groq · 308ms · ~$0.00014
Google 💰 Free tier (most are zero cost)
💎 Gemma 3 27B
Google · 773ms · FREE
🏆 Best Free
⚡ Gemma 3 1B
Google · 694ms · FREE
🔵 Gemini 2.5 Flash
Google · 1640ms · ~$0.000002
🏢 Enterprise (bring your own API key)
🤖 GPT-4o
OpenAI
Enterprise
🧪 Claude 3 Opus
Anthropic
Enterprise
📊 Results
Select models and run comparison
📈 Daily Cost Trend
🔮 30-Day Forecast
Loading forecast...
🏆 Top Tenants by Cost
Loading...
🔍 Hallucination Detection
🔒 PII Redaction
📚 Document Management
🔍 Ask Questions
📊 RAG Stats
Click "Initialize RAG" to start
💰 Budget Configuration
📊 Current Status
Loading budget status...
🔌 MCP Session Management
📚 API Endpoints (140+ Total)
🤖 AI Observability Core
  • POST /api/LlmUsage/track
  • GET /api/LlmUsage/history/{tenantId}
  • GET /api/LlmUsage/cost/{tenantId}
  • GET /api/Optimization/{tenantId}
  • GET /api/Anomaly/detect/{tenantId}
🛡️ Safety & Compliance
  • POST /api/Safety/detect-hallucination
  • POST /api/Safety/redact-pii
🔍 RAG & Search
  • POST /api/rag/query
  • POST /api/rag/documents
  • GET /api/rag/stats/{tenantId}
💰 Budget & Alerts
  • GET /api/Budget/status/{tenantId}
  • POST /api/Budget/check-and-cap/{tenantId}
  • GET /api/Alerts/{tenantId}
📖 Full Swagger Documentation 🧪 Live API Tester

Ready to integrate AI Observability into your project?

One-click deploy script included. Full source code. Lifetime updates.

🚀 Get the Full Platform - $499

Includes 140+ endpoints, 35+ controllers, full source code, and one-click deploy script