AI Manager

Multi-LLM Orchestrator —

Hello! Select a provider and model, then ask me anything.
API Examples

Use the same endpoint with different provider/model parameters:

Expected Response 
{
  "statusCode": 200,
  "data": {
    "trace_id": "...",
    "provider": "openai",
    "model": "gpt-4o",
    "content": "The AI response text",
    "latency_ms": 1234.56,
    "tokens": { "input": 10, "output": 25 }
  }
}