curl --request POST \
  --url https://api.example.com/deploy/llm \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model_name": "<string>",
  "gpu": "L4-24GB",
  "num_gpus": 1,
  "max_batch_size": 96,
  "hf": {
    "repo": "<string>",
    "revision": "<string>",
    "token": "<string>"
  },
  "base_model": "<string>",
  "settings": {
    "min_instances": 1,
    "max_instances": 1
  },
  "extra_args": [
    "<string>"
  ]
}
'

{
  "deploy_id": "<string>",
  "model_name": "<string>",
  "version": "<string>",
  "task": "<string>",
  "status": "<string>",
  "fail_reason": "<string>",
  "created_at": "<string>",
  "updated_at": "<string>",
  "type": "legacy",
  "instances": {
    "running": 123,
    "pending": 123
  },
  "config": {
    "gpu": "L4-24GB",
    "num_gpus": 123,
    "max_batch_size": 123,
    "weights": {
      "repo": "<string>",
      "revision": "<string>",
      "token": "<string>"
    }
  },
  "settings": {
    "min_instances": 1,
    "max_instances": 1
  }
}