Complete API Reference

curl http://localhost:7833/health

{
  "status": "healthy"
}

curl http://localhost:7833/v1/info

{
  "service": "queen-rbee",
  "version": "0.1.0",
  "base_url": "http://localhost:7833",
  "port": 7833
}

curl -X POST http://localhost:7833/v1/jobs \
  -H "Content-Type: application/json" \
  -d '{
    "operation": "spawn_worker",
    "params": {
      "model": "llama-3-8b",
      "worker_type": "cuda",
      "device": 0
    }
  }'

{
  "job_id": "job_abc123",
  "status": "pending",
  "created_at": "2025-11-08T15:30:00Z"
}

curl -N http://localhost:7833/v1/jobs/job_abc123/stream

data: {"event":"job_started","timestamp":"2025-11-08T15:30:01Z"}

data: {"event":"progress","progress":50,"message":"Downloading model..."}

data: {"event":"job_completed","result":{"worker_id":"worker_xyz"}}

curl -X DELETE http://localhost:7833/v1/jobs/job_abc123

{
  "job_id": "job_abc123",
  "status": "cancelled"
}

curl -X POST http://localhost:7833/v1/hive/ready \
  -H "Content-Type: application/json" \
  -d '{
    "hive_id": "localhost",
    "hive_url": "http://localhost:7835"
  }'

curl -N http://localhost:7833/v1/heartbeats/stream

data: {"hive_id":"localhost","status":"healthy","workers":3}

data: {"hive_id":"gpu-server","status":"healthy","workers":5}

curl -X POST http://localhost:7833/v1/shutdown

curl http://localhost:7835/health

ok

curl -X POST http://localhost:7835/v1/jobs \
  -H "Content-Type: application/json" \
  -d '{
    "operation": "download_model",
    "params": {
      "model_id": "meta-llama/Llama-3-8B-GGUF",
      "filename": "llama-3-8b-q4_k_m.gguf"
    }
  }'

curl -N http://localhost:7835/v1/jobs/job_xyz/stream

curl -X DELETE http://localhost:7835/v1/jobs/job_xyz

curl http://localhost:7835/v1/capabilities

{
  "cpu_cores": 16,
  "total_ram_gb": 64,
  "gpus": [
    {
      "id": 0,
      "name": "NVIDIA RTX 3090",
      "vram_gb": 24
    }
  ],
  "workers": [
    {
      "type": "cpu",
      "available": true
    },
    {
      "type": "cuda",
      "available": true
    }
  ]
}

curl -N http://localhost:7835/v1/heartbeats/stream

curl http://localhost:8080/health

OK

curl http://localhost:8080/info

{
  "name": "llm-worker-cuda",
  "version": "0.1.0",
  "worker_type": "cuda",
  "model_loaded": "llama-3-8b-q4_k_m",
  "capabilities": ["text-generation"]
}

curl -X POST http://localhost:8080/v1/infer \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Once upon a time",
    "max_tokens": 100,
    "temperature": 0.7
  }'

{
  "output": "Once upon a time, in a land far away...",
  "tokens_generated": 100,
  "inference_time_ms": 1250
}

curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3-8b",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

export LLORCH_API_TOKEN="your-secure-token"
 
curl -H "Authorization: Bearer $LLORCH_API_TOKEN" \
  http://queen.example.com:7833/v1/info

{
  "error": {
    "code": "invalid_request",
    "message": "Missing required parameter: model"
  }
}

curl -N http://localhost:7833/v1/heartbeats/stream

Content-Type: text/event-stream
Cache-Control: no-cache
Connection: keep-alive

data: {"event":"heartbeat","hive_id":"localhost","timestamp":"2025-11-08T15:30:00Z"}

data: {"event":"worker_spawned","worker_id":"worker_123"}

const eventSource = new EventSource('/v1/heartbeats/stream');
 
eventSource.onerror = () => {
  // Reconnect after delay
  setTimeout(() => {
    eventSource.close();
    // Create new connection
  }, 5000);
};