curl --request POST \
  --url https://ai.cubeuaeai.com/v1beta/models/gemini-3.5-flash:generateContent \
  --header 'Content-Type: application/json' \
  --data '
{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Explain how parallel agent execution works."
        }
      ]
    }
  ],
  "systemInstruction": {
    "parts": [
      {
        "text": "You are a helpful assistant."
      }
    ]
  },
  "generationConfig": {
    "temperature": 1,
    "topP": 1
  },
  "thinkingConfig": {
    "thinkingLevel": "medium"
  }
}
'

import requests

url = "https://ai.cubeuaeai.com/v1beta/models/gemini-3.5-flash:generateContent"

payload = {
    "contents": [
        {
            "role": "user",
            "parts": [{ "text": "Explain how parallel agent execution works." }]
        }
    ],
    "systemInstruction": { "parts": [{ "text": "You are a helpful assistant." }] },
    "generationConfig": {
        "temperature": 1,
        "topP": 1
    },
    "thinkingConfig": { "thinkingLevel": "medium" }
}
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({
    contents: [{role: 'user', parts: [{text: 'Explain how parallel agent execution works.'}]}],
    systemInstruction: {parts: [{text: 'You are a helpful assistant.'}]},
    generationConfig: {temperature: 1, topP: 1},
    thinkingConfig: {thinkingLevel: 'medium'}
  })
};

fetch('https://ai.cubeuaeai.com/v1beta/models/gemini-3.5-flash:generateContent', 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://ai.cubeuaeai.com/v1beta/models/gemini-3.5-flash:generateContent",
  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([
    'contents' => [
        [
                'role' => 'user',
                'parts' => [
                                [
                                                                'text' => 'Explain how parallel agent execution works.'
                                ]
                ]
        ]
    ],
    'systemInstruction' => [
        'parts' => [
                [
                                'text' => 'You are a helpful assistant.'
                ]
        ]
    ],
    'generationConfig' => [
        'temperature' => 1,
        'topP' => 1
    ],
    'thinkingConfig' => [
        'thinkingLevel' => 'medium'
    ]
  ]),
  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://ai.cubeuaeai.com/v1beta/models/gemini-3.5-flash:generateContent"

	payload := strings.NewReader("{\n  \"contents\": [\n    {\n      \"role\": \"user\",\n      \"parts\": [\n        {\n          \"text\": \"Explain how parallel agent execution works.\"\n        }\n      ]\n    }\n  ],\n  \"systemInstruction\": {\n    \"parts\": [\n      {\n        \"text\": \"You are a helpful assistant.\"\n      }\n    ]\n  },\n  \"generationConfig\": {\n    \"temperature\": 1,\n    \"topP\": 1\n  },\n  \"thinkingConfig\": {\n    \"thinkingLevel\": \"medium\"\n  }\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://ai.cubeuaeai.com/v1beta/models/gemini-3.5-flash:generateContent")
  .header("Content-Type", "application/json")
  .body("{\n  \"contents\": [\n    {\n      \"role\": \"user\",\n      \"parts\": [\n        {\n          \"text\": \"Explain how parallel agent execution works.\"\n        }\n      ]\n    }\n  ],\n  \"systemInstruction\": {\n    \"parts\": [\n      {\n        \"text\": \"You are a helpful assistant.\"\n      }\n    ]\n  },\n  \"generationConfig\": {\n    \"temperature\": 1,\n    \"topP\": 1\n  },\n  \"thinkingConfig\": {\n    \"thinkingLevel\": \"medium\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://ai.cubeuaeai.com/v1beta/models/gemini-3.5-flash:generateContent")

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  \"contents\": [\n    {\n      \"role\": \"user\",\n      \"parts\": [\n        {\n          \"text\": \"Explain how parallel agent execution works.\"\n        }\n      ]\n    }\n  ],\n  \"systemInstruction\": {\n    \"parts\": [\n      {\n        \"text\": \"You are a helpful assistant.\"\n      }\n    ]\n  },\n  \"generationConfig\": {\n    \"temperature\": 1,\n    \"topP\": 1\n  },\n  \"thinkingConfig\": {\n    \"thinkingLevel\": \"medium\"\n  }\n}"

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

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "text": "Parallel agent execution allows multiple AI agents to work at the same time..."
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 123,
    "candidatesTokenCount": 123,
    "totalTokenCount": 123
  }
}

{
  "error": {
    "code": 123,
    "message": "<string>",
    "status": "<string>"
  }
}

{
  "error": {
    "code": 123,
    "message": "<string>",
    "status": "<string>"
  }
}