curl --request POST \
  --url https://api.gravixlayer.com/v1/deployments \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "deployment_name": "my-model-deployment",
  "model_name": "meta-llama/llama-3.1-8b-instruct",
  "gpu_model": "NVIDIA_T4_16GB",
  "gpu_count": 1,
  "min_replicas": 1,
  "max_replicas": 5,
  "hw_type": "nvidia-t4-16gb-pcie_1"
}'

{
  "id": "deploy-123456",
  "deployment_name": "my-model-deployment",
  "model_name": "meta-llama/llama-3.1-8b-instruct",
  "gpu_model": "NVIDIA_T4_16GB",
  "gpu_count": 1,
  "min_replicas": 1,
  "max_replicas": 5,
  "hw_type": "nvidia-t4-16gb-pcie_1",
  "status": "creating",
  "created_at": "2025-10-16T18:00:00Z"
}