Create a pod

import os
import time

import requests

API = "https://api.runpod.io"
SESSION = requests.Session()
SESSION.headers["Authorization"] = f"Bearer {os.environ['RUNPOD_API_KEY']}"

# Most preferred GPU first. The loop stops at the first one that places.
GPU_PREFERENCE = [
    "NVIDIA GeForce RTX 4090",
    "NVIDIA GeForce RTX 5090",
    "NVIDIA H100 PCIe",
]
USABLE = {"LOW", "MEDIUM", "HIGH"}  # anything but NONE


def candidates(region):
    """(gpu_id, datacenter_id) pairs that the catalog reports as deployable,
    ordered by GPU_PREFERENCE then by descending stock."""
    response = SESSION.get(
        f"{API}/v2/catalog/datacenters",
        params={"regions": region, "include": "GPU_AVAILABILITY"},
        timeout=30,
    )
    response.raise_for_status()

    rank = {"HIGH": 0, "MEDIUM": 1, "LOW": 2}
    found = []
    for datacenter in response.json()["dataCenters"]:
        for gpu in datacenter.get("gpuAvailability", []):
            if gpu["id"] in GPU_PREFERENCE and gpu["availability"] in USABLE:
                found.append((gpu["id"], datacenter["id"], gpu["availability"]))

    found.sort(key=lambda c: (GPU_PREFERENCE.index(c[0]), rank[c[2]]))
    return [(gpu_id, dc_id) for gpu_id, dc_id, _ in found]


def create(gpu_id, datacenter_id):
    return SESSION.post(
        f"{API}/v2/pods",
        json={
            "name": "inference-worker",
            "image": "runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404",
            "gpu": {"id": gpu_id, "count": 1},
            "dataCenterIds": [datacenter_id],
            "disk": 50,
        },
        timeout=60,
    )


def create_with_backoff(gpu_id, datacenter_id, attempts=5):
    """Rate limits and 5xx are not the candidate's fault, so they are
    retried in place rather than moving to the next GPU."""
    for attempt in range(attempts):
        response = create(gpu_id, datacenter_id)
        if response.status_code == 429:
            # Retry-After is integer seconds on this API.
            time.sleep(int(response.headers.get("Retry-After", 5)))
            continue
        if response.status_code >= 500:
            time.sleep(2**attempt)
            continue
        return response
    raise RuntimeError(f"{attempts} transient failures for {gpu_id}; upstream unhealthy")


def deploy(region="EUROPE"):
    last_detail = None

    for gpu_id, datacenter_id in candidates(region):
        response = create_with_backoff(gpu_id, datacenter_id)

        if response.status_code == 201:
            return response.json()

        problem = response.json()
        last_detail = problem.get("detail")

        if response.status_code == 422:
            # Contract violation — identical on every candidate.
            raise SystemExit(f"Bad request: {problem.get('errors', last_detail)}")
        if response.status_code == 402:
            raise SystemExit(f"Cannot deploy: {last_detail}")
        if response.status_code in (400, 403):
            # 403: no access to this pool. 400: rule violation, or this
            # GPU/data center could not be placed. Either way, move on.
            continue

        response.raise_for_status()

    # Every candidate was refused. A rule violation fails the same way on
    # all of them, so the last detail is the useful signal here.
    raise SystemExit(f"No candidate placed in {region}. Last error: {last_detail}")


if __name__ == "__main__":
    pod = deploy()
    print(f"{pod['id']} placed in {pod['dataCenterId']} on {pod['gpu']['id']}")

curl --request POST \
  --url https://api.runpod.io/v2/pods \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "pytorch-training",
  "image": "runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404",
  "gpu": {
    "id": "NVIDIA GeForce RTX 4090",
    "count": 1
  },
  "disk": 50
}
'

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: 'pytorch-training',
    image: 'runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404',
    gpu: {id: 'NVIDIA GeForce RTX 4090', count: 1},
    disk: 50
  })
};

fetch('https://api.runpod.io/v2/pods', 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.runpod.io/v2/pods",
  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' => 'pytorch-training',
    'image' => 'runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404',
    'gpu' => [
        'id' => 'NVIDIA GeForce RTX 4090',
        'count' => 1
    ],
    'disk' => 50
  ]),
  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.runpod.io/v2/pods"

	payload := strings.NewReader("{\n  \"name\": \"pytorch-training\",\n  \"image\": \"runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404\",\n  \"gpu\": {\n    \"id\": \"NVIDIA GeForce RTX 4090\",\n    \"count\": 1\n  },\n  \"disk\": 50\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.runpod.io/v2/pods")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"pytorch-training\",\n  \"image\": \"runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404\",\n  \"gpu\": {\n    \"id\": \"NVIDIA GeForce RTX 4090\",\n    \"count\": 1\n  },\n  \"disk\": 50\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.runpod.io/v2/pods")

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\": \"pytorch-training\",\n  \"image\": \"runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404\",\n  \"gpu\": {\n    \"id\": \"NVIDIA GeForce RTX 4090\",\n    \"count\": 1\n  },\n  \"disk\": 50\n}"

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

{
  "id": "7h9k2m4n6p",
  "name": "pytorch-training",
  "image": "runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404",
  "args": "",
  "disk": 50,
  "ports": [
    "8888/http",
    "22/tcp"
  ],
  "env": {
    "MODEL_NAME": "llama-3"
  },
  "registry": null,
  "status": "PROVISIONING",
  "actions": [
    "start",
    "terminate"
  ],
  "mounts": {
    "persistent": {
      "size": 20,
      "path": "/workspace"
    }
  },
  "gpu": {
    "id": "NVIDIA GeForce RTX 4090",
    "count": 1
  },
  "cloud": "SECURE",
  "dataCenterId": "US-KS-2",
  "cudaVersion": "12.8",
  "ssh": {
    "proxy": {
      "host": "ssh.runpod.io",
      "port": 22,
      "username": "7h9k2m4n6p-64411eb2",
      "command": "ssh 7h9k2m4n6p-64411eb2@ssh.runpod.io"
    },
    "direct": null
  },
  "template": "9x4m2p7v",
  "cost": 0.44,
  "locked": false,
  "globalNetworking": {
    "enabled": false
  },
  "runtime": {},
  "createdAt": "2026-06-01T12:00:00Z",
  "startedAt": null
}

{
  "title": "Bad Request",
  "status": 400,
  "detail": "request could not be processed"
}

{
  "title": "Unauthorized",
  "status": 401,
  "detail": "missing bearer token"
}

{
  "title": "Forbidden",
  "status": 403,
  "detail": "access denied"
}

{
  "title": "Not Found",
  "status": 404,
  "detail": "resource not found"
}

{
  "title": "Unprocessable Entity",
  "status": 422,
  "detail": "Request validation failed."
}

{
  "title": "Too Many Requests",
  "status": 429,
  "detail": "rate limit exceeded for the minute window"
}

{
  "title": "<string>",
  "status": 123,
  "detail": "<string>",
  "errors": [
    "<string>"
  ]
}