Serverless Containers

Deploy a container deployment template

post/v1/container-deployment-templates/{template_id}/deployments

Request

  • Base URL: https://api.verda.com
  • URL: https://api.verda.com/v1/container-deployment-templates/{template_id}/deployments
  • Auth: HTTP bearer

Path parameters

template_idstring required
Example:qwen3-5-9b

Id of the template

Request body

namestring required

Name of the deployment. Immutable after creation

variantstring

Variant id from the template detail. Defaults to the first variant

featuresstring[]

Feature ids to enable. Defaults to the features marked is_default

hf_token_secret_namestring

Name of an existing secret (POST /secrets) holding a Hugging Face token. Required for gated models

shm_size_mb64 | 128 | 256 | 512 | 1024 | 2048 | 4096 | 8192 | 16384 | 32768

Size of the /dev/shm memory volume in MiB. Defaults to a size based on the GPU count (1 GPU: 1024, 2: 4096, 4: 8192, 8: 16384) or the template default

Example request

{
  "name": "qwen3-5-9b",
  "variant": "fp8",
  "features": [
    "tool_calling",
    "reasoning"
  ],
  "compute": {
    "name": "H100",
    "size": 1
  },
  "hf_token_secret_name": "hf-token",
  "shm_size_mb": 8192,
  "scaling": {
    "min_replica_count": 1,
    "max_replica_count": 50,
    "scale_down_policy": {
      "delay_seconds": 300
    },
    "scale_up_policy": {
      "delay_seconds": 300
    },
    "queue_message_ttl_seconds": 500,
    "concurrent_requests_per_replica": 1,
    "scaling_triggers": {
      "queue_load": {
        "threshold": 2
      },
      "cpu_utilization": {
        "enabled": true,
        "threshold": 80
      },
      "gpu_utilization": {
        "enabled": true,
        "threshold": 80
      }
    }
  }
}

Response

Returns the created container deployment

namestring required

Deployment name

endpoint_base_urlstring required

The base URL of the endpoint

created_atstring required
is_spotboolean required

Example response

{
  "name": "flux",
  "containers": [
    {
      "should_use_cached_image": true,
      "exposed_port": 8080,
      "healthcheck": {
        "enabled": true,
        "port": 8081,
        "path": "/health"
      },
      "entrypoint_overrides": {
        "enabled": true,
        "entrypoint": [
          "python3",
          "main.py"
        ],
        "cmd": [
          "--port",
          "8080"
        ]
      },
      "env": [
        {
          "name": "MY_ENV_VAR",
          "value_or_reference_to_secret": "my-value",
          "type": "plain"
        }
      ],
      "volume_mounts": [
        {
          "type": "scratch",
          "mount_path": "/data"
        }
      ],
      "image": {
        "image": "registry-1.docker.io/chentex/random-logger:v1.0.1",
        "last_updated_at": "2026-10-09T09:42:21.685Z"
      },
      "name": "random-logger-0"
    }
  ],
  "endpoint_base_url": "https://containers.datacrunch.io/flux",
  "created_at": "2021-08-31T12:00:00.000Z",
  "compute": {
    "name": "H100",
    "size": 1
  },
  "container_registry_settings": {
    "is_private": true,
    "credentials": {
      "name": "dockerhub-credentials"
    }
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.