Create deployment

import os
import requests

response = requests.post(
    "https://api.modular.com/v1/deployments",
    headers={
        "Authorization": f"Bearer {os.environ['MODULAR_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={
        "name": "my-gemma-deployment",
        "model_id": "google/gemma-4-31B-it",
        "region_group": "us",
        "scaling": {"min_replicas": 1, "max_replicas": 3},
        "configuration": {
            "model_path": "google/gemma-4-31B-it",
            "engine": "max",
        },
    },
)

deployment = response.json()
print(deployment["status"])

curl -X POST https://api.modular.com/v1/deployments \
  -H "Authorization: Bearer $MODULAR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-gemma-deployment",
    "model_id": "google/gemma-4-31B-it",
    "region_group": "us",
    "scaling": {"min_replicas": 1, "max_replicas": 3},
    "configuration": {
      "model_path": "google/gemma-4-31B-it",
      "engine": "max"
    }
  }'

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: 'my-gemma-deployment',
    model_id: 'google/gemma-4-31B-it',
    region_group: 'us',
    scaling: {min_replicas: 1, max_replicas: 3},
    configuration: {model_path: 'google/gemma-4-31B-it', engine: 'max'}
  })
};

fetch('https://api.modular.com/v1/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.modular.com/v1/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' => 'my-gemma-deployment',
    'model_id' => 'google/gemma-4-31B-it',
    'region_group' => 'us',
    'scaling' => [
        'min_replicas' => 1,
        'max_replicas' => 3
    ],
    'configuration' => [
        'model_path' => 'google/gemma-4-31B-it',
        'engine' => 'max'
    ]
  ]),
  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.modular.com/v1/deployments"

	payload := strings.NewReader("{\n  \"name\": \"my-gemma-deployment\",\n  \"model_id\": \"google/gemma-4-31B-it\",\n  \"region_group\": \"us\",\n  \"scaling\": {\n    \"min_replicas\": 1,\n    \"max_replicas\": 3\n  },\n  \"configuration\": {\n    \"model_path\": \"google/gemma-4-31B-it\",\n    \"engine\": \"max\"\n  }\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.modular.com/v1/deployments")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"my-gemma-deployment\",\n  \"model_id\": \"google/gemma-4-31B-it\",\n  \"region_group\": \"us\",\n  \"scaling\": {\n    \"min_replicas\": 1,\n    \"max_replicas\": 3\n  },\n  \"configuration\": {\n    \"model_path\": \"google/gemma-4-31B-it\",\n    \"engine\": \"max\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.modular.com/v1/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\": \"my-gemma-deployment\",\n  \"model_id\": \"google/gemma-4-31B-it\",\n  \"region_group\": \"us\",\n  \"scaling\": {\n    \"min_replicas\": 1,\n    \"max_replicas\": 3\n  },\n  \"configuration\": {\n    \"model_path\": \"google/gemma-4-31B-it\",\n    \"engine\": \"max\"\n  }\n}"

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

{
  "name": "my-gemma-deployment",
  "model_id": "google/gemma-4-31B-it",
  "status": "deploying",
  "endpoint_url": null,
  "region_group": "us",
  "scaling": {
    "min_replicas": 1,
    "max_replicas": 3
  },
  "configuration": {
    "model_path": "google/gemma-4-31B-it",
    "engine": "max"
  },
  "deployment_id": "cpa9k2xyz",
  "created_at": "2026-04-24T00:00:00Z",
  "created_by": "user@example.com",
  "updated_at": "2026-04-24T00:00:00Z",
  "updated_by": "user@example.com"
}