Skip to main content
POST
/
v1alpha1
/
inference
/
deployments
Create deployment
curl --request POST \
  --url https://api.coreweave.com/v1alpha1/inference/deployments \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "gatewayIds": [
    "<string>"
  ],
  "runtime": {
    "engine": "<string>",
    "version": "<string>",
    "engineConfig": {}
  },
  "resources": {
    "instanceType": "<string>",
    "gpuCount": 123
  },
  "model": {
    "name": "<string>",
    "bucket": "<string>",
    "path": "<string>"
  },
  "autoscaling": {
    "min": 123,
    "max": 123,
    "priority": 123,
    "concurrency": 123,
    "capacityClasses": [
      "CAPACITY_CLASS_RESERVED"
    ]
  },
  "traffic": {
    "weight": 123
  },
  "id": "<string>",
  "disabled": true
}
'
{
  "deployment": {
    "spec": {
      "id": "<string>",
      "name": "<string>",
      "gatewayIds": [
        "<string>"
      ],
      "runtime": {
        "engine": "<string>",
        "version": "<string>",
        "engineConfig": {}
      },
      "resources": {
        "instanceType": "<string>",
        "gpuCount": 123
      },
      "model": {
        "name": "<string>",
        "bucket": "<string>",
        "path": "<string>"
      },
      "autoscaling": {
        "min": 123,
        "max": 123,
        "priority": 123,
        "concurrency": 123,
        "capacityClasses": [
          "CAPACITY_CLASS_RESERVED"
        ]
      },
      "traffic": {
        "weight": 123
      },
      "organizationId": "<string>",
      "disabled": true
    },
    "status": {
      "createdAt": "2023-11-07T05:31:56Z",
      "updatedAt": "2023-11-07T05:31:56Z",
      "conditions": [
        {
          "type": "<string>",
          "lastUpdateTime": "2023-11-07T05:31:56Z",
          "reason": "<string>",
          "message": "<string>",
          "zone": "<string>",
          "status": "True"
        }
      ],
      "status": "STATUS_CREATING"
    }
  }
}

Documentation Index

Fetch the complete documentation index at: https://docs.coreweave.com/llms.txt

Use this file to discover all available pages before exploring further.

A deployment binds a model in CoreWeave AI Object Storage (CAIOS) to one or more gateways. Required fields on the request body: name, gatewayIds, runtime, resources, model, autoscaling, and traffic. The available runtime.engine and runtime.version values are returned by GET /v1alpha1/inference/deployments/parameters.
Example request
curl -X POST https://api.coreweave.com/v1alpha1/inference/deployments \
       -H "Content-Type: application/json" \
       -H "Authorization: Bearer {API_ACCESS_TOKEN}" \
       -d @data.json

Authorizations

​
Authorization
string
header
default:Bearer {API_ACCESS_TOKEN}
required

CoreWeave API access token sent as a bearer token.

Body

application/json

Request for CreateDeployment

​
name
string
required

The name of the deployment

​
gatewayIds
string[]
required

The gateways to associate the deployment with

​
runtime
object
required

Runtime selection and configuration

​
resources
object
required

Resource configuration for the deployment

​
model
object
required

The model configuration

​
autoscaling
object
required

The autoscaling configuration

​
traffic
object
required

The traffic configuration for the deployment

​
id
string

The unique identifier of the deployment, UUID format

​
disabled
boolean

Disable the deployment

Response

OK

Response for CreateDeployment

​
deployment
object

The deployment that was created

Last modified on May 14, 2026