curl --request POST \
  --url https://api.example.com/api/v2/external/inference/create \
  --header 'Content-Type: application/json' \
  --data '
{
  "hf_model_id": "<string>",
  "target_rps": 123,
  "target_latency_p95_ms": 123,
  "stabilisation_window": 123,
  "gpu_type": "<string>",
  "hf_token": "<string>",
  "min_replicas": 1,
  "max_replicas": 1,
  "gpu_count": 1,
  "gpu_vram_gb": 2,
  "vllm_args": "<string>"
}
'

import requests

url = "https://api.example.com/api/v2/external/inference/create"

payload = {
    "hf_model_id": "<string>",
    "target_rps": 123,
    "target_latency_p95_ms": 123,
    "stabilisation_window": 123,
    "gpu_type": "<string>",
    "hf_token": "<string>",
    "min_replicas": 1,
    "max_replicas": 1,
    "gpu_count": 1,
    "gpu_vram_gb": 2,
    "vllm_args": "<string>"
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    hf_model_id: '<string>',
    target_rps: 123,
    target_latency_p95_ms: 123,
    stabilisation_window: 123,
    gpu_type: '<string>',
    hf_token: '<string>',
    min_replicas: 1,
    max_replicas: 1,
    gpu_count: 1,
    gpu_vram_gb: 2,
    vllm_args: '<string>'
  })
};

fetch('https://api.example.com/api/v2/external/inference/create', 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.example.com/api/v2/external/inference/create",
  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([
    'hf_model_id' => '<string>',
    'target_rps' => 123,
    'target_latency_p95_ms' => 123,
    'stabilisation_window' => 123,
    'gpu_type' => '<string>',
    'hf_token' => '<string>',
    'min_replicas' => 1,
    'max_replicas' => 1,
    'gpu_count' => 1,
    'gpu_vram_gb' => 2,
    'vllm_args' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "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.example.com/api/v2/external/inference/create"

	payload := strings.NewReader("{\n  \"hf_model_id\": \"<string>\",\n  \"target_rps\": 123,\n  \"target_latency_p95_ms\": 123,\n  \"stabilisation_window\": 123,\n  \"gpu_type\": \"<string>\",\n  \"hf_token\": \"<string>\",\n  \"min_replicas\": 1,\n  \"max_replicas\": 1,\n  \"gpu_count\": 1,\n  \"gpu_vram_gb\": 2,\n  \"vllm_args\": \"<string>\"\n}")

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

	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.example.com/api/v2/external/inference/create")
  .header("Content-Type", "application/json")
  .body("{\n  \"hf_model_id\": \"<string>\",\n  \"target_rps\": 123,\n  \"target_latency_p95_ms\": 123,\n  \"stabilisation_window\": 123,\n  \"gpu_type\": \"<string>\",\n  \"hf_token\": \"<string>\",\n  \"min_replicas\": 1,\n  \"max_replicas\": 1,\n  \"gpu_count\": 1,\n  \"gpu_vram_gb\": 2,\n  \"vllm_args\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/api/v2/external/inference/create")

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

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"hf_model_id\": \"<string>\",\n  \"target_rps\": 123,\n  \"target_latency_p95_ms\": 123,\n  \"stabilisation_window\": 123,\n  \"gpu_type\": \"<string>\",\n  \"hf_token\": \"<string>\",\n  \"min_replicas\": 1,\n  \"max_replicas\": 1,\n  \"gpu_count\": 1,\n  \"gpu_vram_gb\": 2,\n  \"vllm_args\": \"<string>\"\n}"

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

{
  "deployment_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "status": "<string>"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}