v32

latestOpenAPI 3.1.0raw.githubusercontent.com2026-05-151,1412,2144.5 MB

Everywhere Inference

Update inference deployment

patch/cloud/v3/inference/{project_id}/deployments/{deployment_name}

Path parameters

project_idinteger required

Project ID

Example:1

Project ID

deployment_namestring required

Inference instance name.

Example:my-instance

Inference instance name.

Request body

api_keysstring[] nullable

List of API keys for the inference instance. Multiple keys can be attached to one deployment.If auth_enabled and api_keys are both specified, a ValidationError will be raised.If [] is provided, the API keys will be removed and auth will be disabled on the deployment.

auth_enabledboolean

Set to true to enable API key authentication for the inference instance. "Authorization": "Bearer *****" or "X-Api-Key": "*****" header is required for the requests to the instance if enabled. This field is deprecated and will be removed in the future. Use api_keys field instead.If auth_enabled and api_keys are both specified, a ValidationError will be raised.

commandstring[] nullable

Command to be executed when running a container from an image.

credentials_namestring nullable

Registry credentials name

descriptionstring nullable

Inference instance description.

envsobject nullable

Environment variables for the inference instance.

flavor_namestring

Flavor name for the inference instance.

imagestring nullable

Docker image for the inference instance. This field should contain the image name and tag in the format 'name:tag', e.g., 'nginx:latest'. It defaults to Docker Hub as the image registry, but any accessible Docker image URL can be specified.

listening_portinteger nullable

Listening port for the inference instance.

timeoutinteger nullable

Specifies the duration in seconds without any requests after which the containers will be downscaled to their minimum scale value as defined by scale.min. If set, this helps in optimizing resource usage by reducing the number of container instances during periods of inactivity. The default value when the parameter is not set is 120.

Example request

{
  "api_keys": [
    "key1",
    "key2"
  ],
  "command": [
    "nginx",
    "-g",
    "daemon off;"
  ],
  "containers": [
    {
      "region_id": 1337,
      "scale": {
        "cooldown_period": 60,
        "max": 3,
        "min": 1,
        "polling_interval": 30,
        "triggers": {
          "cpu": {
            "threshold": 75
          },
          "gpu_memory": {
            "threshold": 75
          },
          "gpu_utilization": {
            "threshold": 75
          },
          "http": {
            "rate": 1,
            "window": 60
          },
          "memory": {
            "threshold": 75
          },
          "sqs": {
            "aws_region": "us-east-1",
            "queue_length": 10,
            "queue_url": "https://sqs.us-east-1.amazonaws.com/123456789012/MyQueue"
          }
        }
      }
    }
  ],
  "credentials_name": "dockerhub",
  "description": "My first instance",
  "envs": {
    "DEBUG_MODE": "False",
    "KEY": "12345"
  },
  "flavor_name": "inference-16vcpu-232gib-1xh100-80gb",
  "image": "nginx:latest",
  "ingress_opts": {
    "disable_response_buffering": true
  },
  "listening_port": 80,
  "logging": {
    "destination_region_id": 1,
    "enabled": true,
    "retention_policy": {
      "period": 45
    },
    "topic_name": "my-log-name"
  },
  "probes": {
    "liveness_probe": {
      "enabled": true,
      "probe": {
        "exec": {
          "command": [
            "ls",
            "-l"
          ]
        },
        "failure_threshold": 3,
        "http_get": {
          "headers": {
            "Authorization": "Bearer token 123"
          },
          "host": "127.0.0.1",
          "path": "/healthz",
          "port": 80,
          "schema": "HTTP"
        },
        "period_seconds": 5,
        "success_threshold": 1,
        "tcp_socket": {
          "port": 80
        },
        "timeout_seconds": 1
      }
    },
    "readiness_probe": {
      "enabled": true,
      "probe": {
        "exec": {
          "command": [
            "ls",
            "-l"
          ]
        },
        "failure_threshold": 3,
        "http_get": {
          "headers": {
            "Authorization": "Bearer token 123"
          },
          "host": "127.0.0.1",
          "path": "/healthz",
          "port": 80,
          "schema": "HTTP"
        },
        "period_seconds": 5,
        "success_threshold": 1,
        "tcp_socket": {
          "port": 80
        },
        "timeout_seconds": 1
      }
    },
    "startup_probe": {
      "enabled": true,
      "probe": {
        "exec": {
          "command": [
            "ls",
            "-l"
          ]
        },
        "failure_threshold": 3,
        "http_get": {
          "headers": {
            "Authorization": "Bearer token 123"
          },
          "host": "127.0.0.1",
          "path": "/healthz",
          "port": 80,
          "schema": "HTTP"
        },
        "period_seconds": 5,
        "success_threshold": 1,
        "tcp_socket": {
          "port": 80
        },
        "timeout_seconds": 1
      }
    }
  },
  "timeout": 120
}

Response

tasksstring[] required

List of task IDs representing asynchronous operations. Use these IDs to monitor operation progress:

GET /v1/tasks/{task_id} - Check individual task status and details Poll task status until completion (FINISHED/ERROR) before proceeding with dependent operations.

idstring required

Example response

{
  "tasks": [
    "d478ae29-dedc-4869-82f0-96104425f565"
  ]
}