Create a CoreWeave inference deployment

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": {},
    "engineEnv": {}
  },
  "resources": {
    "instanceType": "<string>",
    "gpuCount": 123
  },
  "model": {
    "name": "<string>",
    "bucket": "<string>",
    "path": "<string>"
  },
  "autoscaling": {
    "min": 123,
    "max": 123,
    "priority": 123,
    "capacityClasses": [],
    "concurrency": 123
  },
  "traffic": {
    "weight": 123
  },
  "id": "<string>",
  "disabled": true
}
'

import requests

url = "https://api.coreweave.com/v1alpha1/inference/deployments"

payload = {
    "name": "<string>",
    "gatewayIds": ["<string>"],
    "runtime": {
        "engine": "<string>",
        "version": "<string>",
        "engineConfig": {},
        "engineEnv": {}
    },
    "resources": {
        "instanceType": "<string>",
        "gpuCount": 123
    },
    "model": {
        "name": "<string>",
        "bucket": "<string>",
        "path": "<string>"
    },
    "autoscaling": {
        "min": 123,
        "max": 123,
        "priority": 123,
        "capacityClasses": [],
        "concurrency": 123
    },
    "traffic": { "weight": 123 },
    "id": "<string>",
    "disabled": True
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    gatewayIds: ['<string>'],
    runtime: {engine: '<string>', version: '<string>', engineConfig: {}, engineEnv: {}},
    resources: {instanceType: '<string>', gpuCount: 123},
    model: {name: '<string>', bucket: '<string>', path: '<string>'},
    autoscaling: {min: 123, max: 123, priority: 123, capacityClasses: [], concurrency: 123},
    traffic: {weight: 123},
    id: '<string>',
    disabled: true
  })
};

fetch('https://api.coreweave.com/v1alpha1/inference/deployments', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.coreweave.com/v1alpha1/inference/deployments",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => '<string>',
    'gatewayIds' => [
        '<string>'
    ],
    'runtime' => [
        'engine' => '<string>',
        'version' => '<string>',
        'engineConfig' => [
                
        ],
        'engineEnv' => [
                
        ]
    ],
    'resources' => [
        'instanceType' => '<string>',
        'gpuCount' => 123
    ],
    'model' => [
        'name' => '<string>',
        'bucket' => '<string>',
        'path' => '<string>'
    ],
    'autoscaling' => [
        'min' => 123,
        'max' => 123,
        'priority' => 123,
        'capacityClasses' => [
                
        ],
        'concurrency' => 123
    ],
    'traffic' => [
        'weight' => 123
    ],
    'id' => '<string>',
    'disabled' => true
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.coreweave.com/v1alpha1/inference/deployments"

	payload := strings.NewReader("{\n  \"name\": \"<string>\",\n  \"gatewayIds\": [\n    \"<string>\"\n  ],\n  \"runtime\": {\n    \"engine\": \"<string>\",\n    \"version\": \"<string>\",\n    \"engineConfig\": {},\n    \"engineEnv\": {}\n  },\n  \"resources\": {\n    \"instanceType\": \"<string>\",\n    \"gpuCount\": 123\n  },\n  \"model\": {\n    \"name\": \"<string>\",\n    \"bucket\": \"<string>\",\n    \"path\": \"<string>\"\n  },\n  \"autoscaling\": {\n    \"min\": 123,\n    \"max\": 123,\n    \"priority\": 123,\n    \"capacityClasses\": [],\n    \"concurrency\": 123\n  },\n  \"traffic\": {\n    \"weight\": 123\n  },\n  \"id\": \"<string>\",\n  \"disabled\": true\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.coreweave.com/v1alpha1/inference/deployments")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\",\n  \"gatewayIds\": [\n    \"<string>\"\n  ],\n  \"runtime\": {\n    \"engine\": \"<string>\",\n    \"version\": \"<string>\",\n    \"engineConfig\": {},\n    \"engineEnv\": {}\n  },\n  \"resources\": {\n    \"instanceType\": \"<string>\",\n    \"gpuCount\": 123\n  },\n  \"model\": {\n    \"name\": \"<string>\",\n    \"bucket\": \"<string>\",\n    \"path\": \"<string>\"\n  },\n  \"autoscaling\": {\n    \"min\": 123,\n    \"max\": 123,\n    \"priority\": 123,\n    \"capacityClasses\": [],\n    \"concurrency\": 123\n  },\n  \"traffic\": {\n    \"weight\": 123\n  },\n  \"id\": \"<string>\",\n  \"disabled\": true\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.coreweave.com/v1alpha1/inference/deployments")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"<string>\",\n  \"gatewayIds\": [\n    \"<string>\"\n  ],\n  \"runtime\": {\n    \"engine\": \"<string>\",\n    \"version\": \"<string>\",\n    \"engineConfig\": {},\n    \"engineEnv\": {}\n  },\n  \"resources\": {\n    \"instanceType\": \"<string>\",\n    \"gpuCount\": 123\n  },\n  \"model\": {\n    \"name\": \"<string>\",\n    \"bucket\": \"<string>\",\n    \"path\": \"<string>\"\n  },\n  \"autoscaling\": {\n    \"min\": 123,\n    \"max\": 123,\n    \"priority\": 123,\n    \"capacityClasses\": [],\n    \"concurrency\": 123\n  },\n  \"traffic\": {\n    \"weight\": 123\n  },\n  \"id\": \"<string>\",\n  \"disabled\": true\n}"

response = http.request(request)
puts response.read_body

{
  "deployment": {
    "spec": {
      "id": "<string>",
      "name": "<string>",
      "gatewayIds": [
        "<string>"
      ],
      "runtime": {
        "engine": "<string>",
        "version": "<string>",
        "engineConfig": {},
        "engineEnv": {}
      },
      "resources": {
        "instanceType": "<string>",
        "gpuCount": 123
      },
      "model": {
        "name": "<string>",
        "bucket": "<string>",
        "path": "<string>"
      },
      "autoscaling": {
        "min": 123,
        "max": 123,
        "priority": 123,
        "capacityClasses": [
          "CAPACITY_CLASS_RESERVED"
        ],
        "concurrency": 123
      },
      "traffic": {
        "weight": 123
      },
      "organizationId": "<string>",
      "disabled": true,
      "hotLoad": {
        "bucket": "<string>",
        "transitionMode": 123,
        "pathPrefix": "<string>"
      }
    },
    "status": {
      "createdAt": "2023-11-07T05:31:56Z",
      "updatedAt": "2023-11-07T05:31:56Z",
      "status": "STATUS_UNSPECIFIED",
      "conditions": [
        {
          "type": "<string>",
          "status": "STATUS_UNSPECIFIED",
          "lastUpdateTime": "2023-11-07T05:31:56Z",
          "reason": "<string>",
          "message": "<string>",
          "zone": "<string>"
        }
      ]
    }
  }
}

{
  "code": 123,
  "message": "<string>",
  "details": [
    {
      "@type": "<string>"
    }
  ]
}

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": {},
    "engineEnv": {}
  },
  "resources": {
    "instanceType": "<string>",
    "gpuCount": 123
  },
  "model": {
    "name": "<string>",
    "bucket": "<string>",
    "path": "<string>"
  },
  "autoscaling": {
    "min": 123,
    "max": 123,
    "priority": 123,
    "capacityClasses": [],
    "concurrency": 123
  },
  "traffic": {
    "weight": 123
  },
  "id": "<string>",
  "disabled": true
}
'

import requests

url = "https://api.coreweave.com/v1alpha1/inference/deployments"

payload = {
    "name": "<string>",
    "gatewayIds": ["<string>"],
    "runtime": {
        "engine": "<string>",
        "version": "<string>",
        "engineConfig": {},
        "engineEnv": {}
    },
    "resources": {
        "instanceType": "<string>",
        "gpuCount": 123
    },
    "model": {
        "name": "<string>",
        "bucket": "<string>",
        "path": "<string>"
    },
    "autoscaling": {
        "min": 123,
        "max": 123,
        "priority": 123,
        "capacityClasses": [],
        "concurrency": 123
    },
    "traffic": { "weight": 123 },
    "id": "<string>",
    "disabled": True
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    gatewayIds: ['<string>'],
    runtime: {engine: '<string>', version: '<string>', engineConfig: {}, engineEnv: {}},
    resources: {instanceType: '<string>', gpuCount: 123},
    model: {name: '<string>', bucket: '<string>', path: '<string>'},
    autoscaling: {min: 123, max: 123, priority: 123, capacityClasses: [], concurrency: 123},
    traffic: {weight: 123},
    id: '<string>',
    disabled: true
  })
};

fetch('https://api.coreweave.com/v1alpha1/inference/deployments', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.coreweave.com/v1alpha1/inference/deployments",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => '<string>',
    'gatewayIds' => [
        '<string>'
    ],
    'runtime' => [
        'engine' => '<string>',
        'version' => '<string>',
        'engineConfig' => [
                
        ],
        'engineEnv' => [
                
        ]
    ],
    'resources' => [
        'instanceType' => '<string>',
        'gpuCount' => 123
    ],
    'model' => [
        'name' => '<string>',
        'bucket' => '<string>',
        'path' => '<string>'
    ],
    'autoscaling' => [
        'min' => 123,
        'max' => 123,
        'priority' => 123,
        'capacityClasses' => [
                
        ],
        'concurrency' => 123
    ],
    'traffic' => [
        'weight' => 123
    ],
    'id' => '<string>',
    'disabled' => true
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.coreweave.com/v1alpha1/inference/deployments"

	payload := strings.NewReader("{\n  \"name\": \"<string>\",\n  \"gatewayIds\": [\n    \"<string>\"\n  ],\n  \"runtime\": {\n    \"engine\": \"<string>\",\n    \"version\": \"<string>\",\n    \"engineConfig\": {},\n    \"engineEnv\": {}\n  },\n  \"resources\": {\n    \"instanceType\": \"<string>\",\n    \"gpuCount\": 123\n  },\n  \"model\": {\n    \"name\": \"<string>\",\n    \"bucket\": \"<string>\",\n    \"path\": \"<string>\"\n  },\n  \"autoscaling\": {\n    \"min\": 123,\n    \"max\": 123,\n    \"priority\": 123,\n    \"capacityClasses\": [],\n    \"concurrency\": 123\n  },\n  \"traffic\": {\n    \"weight\": 123\n  },\n  \"id\": \"<string>\",\n  \"disabled\": true\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.coreweave.com/v1alpha1/inference/deployments")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\",\n  \"gatewayIds\": [\n    \"<string>\"\n  ],\n  \"runtime\": {\n    \"engine\": \"<string>\",\n    \"version\": \"<string>\",\n    \"engineConfig\": {},\n    \"engineEnv\": {}\n  },\n  \"resources\": {\n    \"instanceType\": \"<string>\",\n    \"gpuCount\": 123\n  },\n  \"model\": {\n    \"name\": \"<string>\",\n    \"bucket\": \"<string>\",\n    \"path\": \"<string>\"\n  },\n  \"autoscaling\": {\n    \"min\": 123,\n    \"max\": 123,\n    \"priority\": 123,\n    \"capacityClasses\": [],\n    \"concurrency\": 123\n  },\n  \"traffic\": {\n    \"weight\": 123\n  },\n  \"id\": \"<string>\",\n  \"disabled\": true\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.coreweave.com/v1alpha1/inference/deployments")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"<string>\",\n  \"gatewayIds\": [\n    \"<string>\"\n  ],\n  \"runtime\": {\n    \"engine\": \"<string>\",\n    \"version\": \"<string>\",\n    \"engineConfig\": {},\n    \"engineEnv\": {}\n  },\n  \"resources\": {\n    \"instanceType\": \"<string>\",\n    \"gpuCount\": 123\n  },\n  \"model\": {\n    \"name\": \"<string>\",\n    \"bucket\": \"<string>\",\n    \"path\": \"<string>\"\n  },\n  \"autoscaling\": {\n    \"min\": 123,\n    \"max\": 123,\n    \"priority\": 123,\n    \"capacityClasses\": [],\n    \"concurrency\": 123\n  },\n  \"traffic\": {\n    \"weight\": 123\n  },\n  \"id\": \"<string>\",\n  \"disabled\": true\n}"

response = http.request(request)
puts response.read_body

{
  "deployment": {
    "spec": {
      "id": "<string>",
      "name": "<string>",
      "gatewayIds": [
        "<string>"
      ],
      "runtime": {
        "engine": "<string>",
        "version": "<string>",
        "engineConfig": {},
        "engineEnv": {}
      },
      "resources": {
        "instanceType": "<string>",
        "gpuCount": 123
      },
      "model": {
        "name": "<string>",
        "bucket": "<string>",
        "path": "<string>"
      },
      "autoscaling": {
        "min": 123,
        "max": 123,
        "priority": 123,
        "capacityClasses": [
          "CAPACITY_CLASS_RESERVED"
        ],
        "concurrency": 123
      },
      "traffic": {
        "weight": 123
      },
      "organizationId": "<string>",
      "disabled": true,
      "hotLoad": {
        "bucket": "<string>",
        "transitionMode": 123,
        "pathPrefix": "<string>"
      }
    },
    "status": {
      "createdAt": "2023-11-07T05:31:56Z",
      "updatedAt": "2023-11-07T05:31:56Z",
      "status": "STATUS_UNSPECIFIED",
      "conditions": [
        {
          "type": "<string>",
          "status": "STATUS_UNSPECIFIED",
          "lastUpdateTime": "2023-11-07T05:31:56Z",
          "reason": "<string>",
          "message": "<string>",
          "zone": "<string>"
        }
      ]
    }
  }
}

{
  "code": 123,
  "message": "<string>",
  "details": [
    {
      "@type": "<string>"
    }
  ]
}

The API server is https://api.coreweave.com.
Replace {API_ACCESS_TOKEN} with your CoreWeave API access token.
For required permissions, see IAM Access Policies.

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

Autorisations

Authorization

string

header

défaut:Bearer {API_ACCESS_TOKEN}

requis

CoreWeave API access token sent as a bearer token.

Corps

application/json

Request for CreateDeployment

name

string

requis

The name of the deployment

gatewayIds

string[]

requis

The gateways to associate the deployment with

runtime

object

requis

Runtime selection and configuration

Show child attributes

resources

object

requis

Resource configuration for the deployment

Show child attributes

model

object

requis

The model configuration

Show child attributes

autoscaling

object

requis

The autoscaling configuration

Show child attributes

traffic

object

requis

The traffic configuration for the deployment

Show child attributes

string

The unique identifier of the deployment, UUID format

disabled

boolean

Disable the deployment

hotLoad

object

The hot-load configuration for the deployment. Set it to enable checkpoint hot-loading; it is immutable after creation.

Show child attributes

Réponse

Response for CreateDeployment

deployment

object

The deployment that was created

Show child attributes

Dernière modification le 30 septembre 2026