LLM Request Simulator

Send requests and watch intelligent routing in action

Current: 45% Healthy

Real-Time Routing

0 Requests
0ms Avg Latency
$0.00 Saved
Request
Plexor Gateway
Analyzing request...
Mistral
$0.0002/1K
0
GPT-4o-mini
$0.0015/1K
0
Azure OpenAI
$0.03/1K
0
Claude
$0.015/1K
0

Request Log

Send a request to see routing decisions...

Analytics Dashboard

Real-time insights and cost analysis

Cost Savings Calculator

Without Plexor $15,000
With Plexor $5,700
Monthly Savings $9,300 (62%)

Provider Distribution

OneLake Telemetry

llm_telemetry.delta Live 
{
  "timestamp": "2026-01-06T09:47:23Z",
  "request_id": "req_fabric_001",
  "provider": "mistral",
  "model": "mistral-small",
  "tokens_in": 45,
  "tokens_out": 128,
  "latency_ms": 234,
  "cost_usd": 0.000035,
  "routing_decision": "cost_optimized",
  "fabric_capacity_used": false
}

Fabric Capacity Simulation

At 45% capacity, requests are routed to Azure OpenAI when optimal.