> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apimart.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI Multimodal Responses API

>  - Sepenuhnya kompatibel dengan format OpenAI Responses API
- Mendukung input multimodal berupa teks dan gambar
- Mendukung ekstensi tool: pencarian web, pencarian file, pemanggilan fungsi, dan remote MCP 

<RequestExample>
  ```bash cURL theme={null}
  curl https://api.apimart.ai/v1/responses \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer <token>" \
    -d '{
      "model": "gpt-5.2-pro",
      "input": [
        {
          "role": "user",
          "content": [
            {
              "type": "input_text",
              "text": "What is in this image?"
            },
            {
              "type": "input_image",
              "image_url": "https://openai-documentation.vercel.app/images/cat_and_otter.png"
            }
          ]
        }
      ]
    }'
  ```

  ```python Python theme={null}
  import requests
  import os

  url = "https://api.apimart.ai/v1/responses"

  payload = {
      "model": "gpt-5.2-pro",
      "input": [
          {
              "role": "user",
              "content": [
                  {
                      "type": "input_text",
                      "text": "What is in this image?"
                  },
                  {
                      "type": "input_image",
                      "image_url": "https://openai-documentation.vercel.app/images/cat_and_otter.png"
                  }
              ]
          }
      ]
  }

  headers = {
      "Authorization": f"Bearer {os.environ.get('OPENAI_API_KEY')}",
      "Content-Type": "application/json"
  }

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

  print(response.json())
  ```

  ```javascript JavaScript theme={null}
  const url = "https://api.apimart.ai/v1/responses";

  const payload = {
    model: "gpt-5.2-pro",
    input: [
      {
        role: "user",
        content: [
          {
            type: "input_text",
            text: "What is in this image?"
          },
          {
            type: "input_image",
            image_url: "https://openai-documentation.vercel.app/images/cat_and_otter.png"
          }
        ]
      }
    ]
  };

  const headers = {
    "Authorization": `Bearer ${process.env.OPENAI_API_KEY}`,
    "Content-Type": "application/json"
  };

  fetch(url, {
    method: "POST",
    headers: headers,
    body: JSON.stringify(payload)
  })
    .then(response => response.json())
    .then(data => console.log(data))
    .catch(error => console.error('Error:', error));
  ```

  ```go Go theme={null}
  package main

  import (
      "bytes"
      "encoding/json"
      "fmt"
      "io/ioutil"
      "net/http"
      "os"
  )

  func main() {
      url := "https://api.apimart.ai/v1/responses"

      payload := map[string]interface{}{
          "model": "gpt-5.2-pro",
          "input": []map[string]interface{}{
              {
                  "role": "user",
                  "content": []map[string]string{
                      {
                          "type": "input_text",
                          "text": "What is in this image?",
                      },
                      {
                          "type":      "input_image",
                          "image_url": "https://openai-documentation.vercel.app/images/cat_and_otter.png",
                      },
                  },
              },
          },
      }

      jsonData, _ := json.Marshal(payload)

      req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
      req.Header.Set("Authorization", "Bearer "+os.Getenv("OPENAI_API_KEY"))
      req.Header.Set("Content-Type", "application/json")

      client := &http.Client{}
      resp, err := client.Do(req)
      if err != nil {
          panic(err)
      }
      defer resp.Body.Close()

      body, _ := ioutil.ReadAll(resp.Body)
      fmt.Println(string(body))
  }
  ```

  ```java Java theme={null}
  import java.net.http.HttpClient;
  import java.net.http.HttpRequest;
  import java.net.http.HttpResponse;
  import java.net.URI;

  public class Main {
      public static void main(String[] args) throws Exception {
          String url = "https://api.apimart.ai/v1/responses";
          String apiKey = System.getenv("OPENAI_API_KEY");

          String payload = """
          {
            "model": "gpt-5.2-pro",
            "input": [
              {
                "role": "user",
                "content": [
                  {
                    "type": "input_text",
                    "text": "What is in this image?"
                  },
                  {
                    "type": "input_image",
                    "image_url": "https://openai-documentation.vercel.app/images/cat_and_otter.png"
                  }
                ]
              }
            ]
          }
          """;

          HttpClient client = HttpClient.newHttpClient();
          HttpRequest request = HttpRequest.newBuilder()
              .uri(URI.create(url))
              .header("Authorization", "Bearer " + apiKey)
              .header("Content-Type", "application/json")
              .POST(HttpRequest.BodyPublishers.ofString(payload))
              .build();

          HttpResponse<String> response = client.send(request,
              HttpResponse.BodyHandlers.ofString());

          System.out.println(response.body());
      }
  }
  ```

  ```php PHP theme={null}
  <?php

  $url = "https://api.apimart.ai/v1/responses";
  $apiKey = getenv('OPENAI_API_KEY');

  $payload = [
      "model" => "gpt-5.2-pro",
      "input" => [
          [
              "role" => "user",
              "content" => [
                  [
                      "type" => "input_text",
                      "text" => "What is in this image?"
                  ],
                  [
                      "type" => "input_image",
                      "image_url" => "https://openai-documentation.vercel.app/images/cat_and_otter.png"
                  ]
              ]
          ]
      ]
  ];

  $ch = curl_init($url);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
  curl_setopt($ch, CURLOPT_POST, true);
  curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
  curl_setopt($ch, CURLOPT_HTTPHEADER, [
      "Authorization: Bearer " . $apiKey,
      "Content-Type: application/json"
  ]);

  $response = curl_exec($ch);
  curl_close($ch);

  echo $response;
  ?>
  ```

  ```ruby Ruby theme={null}
  require 'net/http'
  require 'json'
  require 'uri'

  url = URI("https://api.apimart.ai/v1/responses")
  api_key = ENV['OPENAI_API_KEY']

  payload = {
    model: "gpt-5.2-pro",
    input: [
      {
        role: "user",
        content: [
          {
            type: "input_text",
            text: "What is in this image?"
          },
          {
            type: "input_image",
            image_url: "https://openai-documentation.vercel.app/images/cat_and_otter.png"
          }
        ]
      }
    ]
  }

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

  request = Net::HTTP::Post.new(url)
  request["Authorization"] = "Bearer #{api_key}"
  request["Content-Type"] = "application/json"
  request.body = payload.to_json

  response = http.request(request)
  puts response.body
  ```

  ```swift Swift theme={null}
  import Foundation

  let url = URL(string: "https://api.apimart.ai/v1/responses")!
  let apiKey = ProcessInfo.processInfo.environment["OPENAI_API_KEY"] ?? ""

  let payload: [String: Any] = [
      "model": "gpt-5.2-pro",
      "input": [
          [
              "role": "user",
              "content": [
                  [
                      "type": "input_text",
                      "text": "What is in this image?"
                  ],
                  [
                      "type": "input_image",
                      "image_url": "https://openai-documentation.vercel.app/images/cat_and_otter.png"
                  ]
              ]
          ]
      ]
  ]

  var request = URLRequest(url: url)
  request.httpMethod = "POST"
  request.setValue("Bearer \(apiKey)", forHTTPHeaderField: "Authorization")
  request.setValue("application/json", forHTTPHeaderField: "Content-Type")
  request.httpBody = try? JSONSerialization.data(withJSONObject: payload)

  let task = URLSession.shared.dataTask(with: request) { data, response, error in
      if let error = error {
          print("Error: \(error)")
          return
      }

      if let data = data, let responseString = String(data: data, encoding: .utf8) {
          print(responseString)
      }
  }

  task.resume()
  ```

  ```csharp C# theme={null}
  using System;
  using System.Net.Http;
  using System.Text;
  using System.Threading.Tasks;

  class Program
  {
      static async Task Main(string[] args)
      {
          var url = "https://api.apimart.ai/v1/responses";
          var apiKey = Environment.GetEnvironmentVariable("OPENAI_API_KEY");

          var payload = @"{
              ""model"": ""gpt-5.2-pro"",
              ""input"": [
                  {
                      ""role"": ""user"",
                      ""content"": [
                          {
                              ""type"": ""input_text"",
                              ""text"": ""What is in this image?""
                          },
                          {
                              ""type"": ""input_image"",
                              ""image_url"": ""https://openai-documentation.vercel.app/images/cat_and_otter.png""
                          }
                      ]
                  }
              ]
          }";

          using var client = new HttpClient();
          client.DefaultRequestHeaders.Add("Authorization", $"Bearer {apiKey}");

          var content = new StringContent(payload, Encoding.UTF8, "application/json");
          var response = await client.PostAsync(url, content);
          var result = await response.Content.ReadAsStringAsync();

          Console.WriteLine(result);
      }
  }
  ```

  ```c C theme={null}
  #include <stdio.h>
  #include <curl/curl.h>
  #include <stdlib.h>

  int main(void) {
      CURL *curl;
      CURLcode res;
      const char *api_key = getenv("OPENAI_API_KEY");

      curl_global_init(CURL_GLOBAL_DEFAULT);
      curl = curl_easy_init();

      if(curl) {
          const char *url = "https://api.apimart.ai/v1/responses";
          const char *payload = "{"
              "\"model\":\"gpt-5.2-pro\","
              "\"input\":[{\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is in this image?\"},{\"type\":\"input_image\",\"image_url\":\"https://openai-documentation.vercel.app/images/cat_and_otter.png\"}]}]"
          "}";

          char auth_header[256];
          snprintf(auth_header, sizeof(auth_header), "Authorization: Bearer %s", api_key);

          struct curl_slist *headers = NULL;
          headers = curl_slist_append(headers, auth_header);
          headers = curl_slist_append(headers, "Content-Type: application/json");

          curl_easy_setopt(curl, CURLOPT_URL, url);
          curl_easy_setopt(curl, CURLOPT_POSTFIELDS, payload);
          curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);

          res = curl_easy_perform(curl);

          if(res != CURLE_OK) {
              fprintf(stderr, "curl_easy_perform() failed: %s\n",
                      curl_easy_strerror(res));
          }

          curl_slist_free_all(headers);
          curl_easy_cleanup(curl);
      }

      curl_global_cleanup();
      return 0;
  }
  ```

  ```objectivec Objective-C theme={null}
  #import <Foundation/Foundation.h>

  int main(int argc, const char * argv[]) {
      @autoreleasepool {
          NSURL *url = [NSURL URLWithString:@"https://api.apimart.ai/v1/responses"];
          NSString *apiKey = [NSProcessInfo processInfo].environment[@"OPENAI_API_KEY"];

          NSDictionary *payload = @{
              @"model": @"gpt-5.2-pro",
              @"input": @[
                  @{
                      @"role": @"user",
                      @"content": @[
                          @{
                              @"type": @"input_text",
                              @"text": @"What is in this image?"
                          },
                          @{
                              @"type": @"input_image",
                              @"image_url": @"https://openai-documentation.vercel.app/images/cat_and_otter.png"
                          }
                      ]
                  }
              ]
          };

          NSError *error;
          NSData *jsonData = [NSJSONSerialization dataWithJSONObject:payload
                                                            options:0
                                                              error:&error];

          NSMutableURLRequest *request = [NSMutableURLRequest requestWithURL:url];
          [request setHTTPMethod:@"POST"];
          [request setValue:[NSString stringWithFormat:@"Bearer %@", apiKey]
              forHTTPHeaderField:@"Authorization"];
          [request setValue:@"application/json" forHTTPHeaderField:@"Content-Type"];
          [request setHTTPBody:jsonData];

          NSURLSessionDataTask *task = [[NSURLSession sharedSession]
              dataTaskWithRequest:request
              completionHandler:^(NSData *data, NSURLResponse *response, NSError *error) {
                  if (error) {
                      NSLog(@"Error: %@", error);
                      return;
                  }
                  NSString *result = [[NSString alloc] initWithData:data
                                                          encoding:NSUTF8StringEncoding];
                  NSLog(@"%@", result);
              }];

          [task resume];
          [[NSRunLoop mainRunLoop] run];
      }
      return 0;
  }
  ```

  ```ocaml OCaml theme={null}
  (* Requires cohttp and yojson libraries *)
  open Lwt
  open Cohttp
  open Cohttp_lwt_unix

  let url = "https://api.apimart.ai/v1/responses"
  let api_key = Sys.getenv "OPENAI_API_KEY"

  let payload = {|{
    "model": "gpt-5.2-pro",
    "input": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_text",
            "text": "What is in this image?"
          },
          {
            "type": "input_image",
            "image_url": "https://openai-documentation.vercel.app/images/cat_and_otter.png"
          }
        ]
      }
    ]
  }|}

  let () =
    let headers = Header.init ()
      |> fun h -> Header.add h "Authorization" ("Bearer " ^ api_key)
      |> fun h -> Header.add h "Content-Type" "application/json"
    in
    let body = Cohttp_lwt.Body.of_string payload in

    let response = Client.post ~headers ~body (Uri.of_string url) >>= fun (resp, body) ->
      body |> Cohttp_lwt.Body.to_string >|= fun body_str ->
      print_endline body_str
    in
    Lwt_main.run response
  ```

  ```dart Dart theme={null}
  import 'dart:convert';
  import 'dart:io';
  import 'package:http/http.dart' as http;

  void main() async {
    final url = Uri.parse('https://api.apimart.ai/v1/responses');
    final apiKey = Platform.environment['OPENAI_API_KEY'];

    final payload = {
      'model': 'gpt-5.2-pro',
      'input': [
        {
          'role': 'user',
          'content': [
            {
              'type': 'input_text',
              'text': 'What is in this image?'
            },
            {
              'type': 'input_image',
              'image_url': 'https://openai-documentation.vercel.app/images/cat_and_otter.png'
            }
          ]
        }
      ]
    };

    final response = await http.post(
      url,
      headers: {
        'Authorization': 'Bearer $apiKey',
        'Content-Type': 'application/json',
      },
      body: jsonEncode(payload),
    );

    print(response.body);
  }
  ```

  ```r R theme={null}
  library(httr)
  library(jsonlite)

  url <- "https://api.apimart.ai/v1/responses"
  api_key <- Sys.getenv("OPENAI_API_KEY")

  payload <- list(
    model = "gpt-5.2-pro",
    input = list(
      list(
        role = "user",
        content = list(
          list(
            type = "input_text",
            text = "What is in this image?"
          ),
          list(
            type = "input_image",
            image_url = "https://openai-documentation.vercel.app/images/cat_and_otter.png"
          )
        )
      )
    )
  )

  response <- POST(
    url,
    add_headers(
      Authorization = paste("Bearer", api_key),
      `Content-Type` = "application/json"
    ),
    body = toJSON(payload, auto_unbox = TRUE),
    encode = "raw"
  )

  cat(content(response, "text"))
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "code": 200,
    "data": {
      "id": "resp-9876543210",
      "object": "response",
      "created": 1677652288,
      "model": "gpt-5.2-pro",
      "choices": [
        {
          "index": 0,
          "message": {
            "role": "assistant",
            "content": "This image shows a cat and an otter. They appear to be interacting with each other in a very cute and heartwarming scene. The cat and otter seem to be getting along well."
          },
          "finish_reason": "stop"
        }
      ],
      "usage": {
        "prompt_tokens": 156,
        "completion_tokens": 45,
        "total_tokens": 201
      }
    }
  }
  ```

  ```json 400 theme={null}
  {
    "error": {
      "code": 400,
      "message": "Invalid request parameters",
      "type": "invalid_request_error"
    }
  }
  ```

  ```json 401 theme={null}
  {
    "error": {
      "code": 401,
      "message": "Authentication failed, please check your API key",
      "type": "authentication_error"
    }
  }
  ```

  ```json 402 theme={null}
  {
    "error": {
      "code": 402,
      "message": "Insufficient account balance, please top up and try again",
      "type": "payment_required"
    }
  }
  ```

  ```json 403 theme={null}
  {
    "error": {
      "code": 403,
      "message": "Access forbidden, you do not have permission to access this resource",
      "type": "permission_error"
    }
  }
  ```

  ```json 429 theme={null}
  {
    "error": {
      "code": 429,
      "message": "Too many requests, please try again later",
      "type": "rate_limit_error"
    }
  }
  ```

  ```json 500 theme={null}
  {
    "error": {
      "code": 500,
      "message": "Internal server error, please try again later",
      "type": "server_error"
    }
  }
  ```

  ```json 502 theme={null}
  {
    "error": {
      "code": 502,
      "message": "Gateway error, server temporarily unavailable",
      "type": "bad_gateway"
    }
  }
  ```
</ResponseExample>

## Otorisasi

<ParamField header="Authorization" type="string" required>
  \##Semua API memerlukan autentikasi Bearer Token##

  Dapatkan API Key:

  Kunjungi [Halaman Manajemen API Key](https://apimart.ai/keys) untuk mendapatkan API Key Anda

  Tambahkan ke header request:

  ```
  Authorization: Bearer YOUR_API_KEY
  ```
</ParamField>

## Body

<ParamField body="model" type="string" required default="gpt-5.2-pro">
  Nama model

  Model yang didukung meliputi:

  * `gpt-5.2-pro`
  * `gpt-5.2-codex`
  * Model lainnya segera hadir...
</ParamField>

<ParamField body="input" type="array" required>
  Daftar konten input

  Array input; setiap item berisi field `role` dan `content`.

  **💡 Pengisian cepat (area Try it):**

  1. Klik "+ Add an item" untuk menambahkan item input
  2. Input `role`: `user` (pesan pengguna), `assistant` (respons AI), atau `system` (prompt sistem)
  3. Tambahkan blok konten di `content` (dapat mencakup teks dan gambar)

  <Expandable title="Detail field">
    <ParamField body="role" type="string" required default="user">
      Jenis role

      Opsi: `user` (pesan pengguna), `assistant` (respons AI, untuk multi-giliran), `system` (prompt sistem, untuk mengatur perilaku AI)
    </ParamField>

    <ParamField body="content" type="array" required>
      Array konten

      Mendukung berbagai jenis blok konten, termasuk teks dan gambar.

      <Expandable title="Jenis blok konten">
        <ParamField body="type" type="string" required>
          Jenis konten

          Opsi:

          * `input_text`: Input teks
          * `input_image`: Input gambar
        </ParamField>

        <ParamField body="text" type="string">
          Konten teks

          Digunakan saat `type` adalah `input_text`; isi dengan konten teks
        </ParamField>

        <ParamField body="image_url" type="string">
          URL gambar

          Digunakan saat `type` adalah `input_image`; isi dengan URL gambar atau encoding Base64

          Mendukung dua format:

          **1. URL gambar lengkap**

          * URL gambar yang dapat diakses publik (http\:// atau https\://)
          * Contoh: `https://example.com/image.jpg`

          **2. Format yang dikodekan Base64**

          * **Harus menggunakan format Data URI lengkap**
          * Format: `data:image/{format};base64,{base64_data}`
          * Format gambar yang didukung: jpeg, png, gif, webp
        </ParamField>
      </Expandable>
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="temperature" type="number">
  Mengontrol keacakan output, rentang 0-2

  * Nilai yang lebih rendah (misalnya 0,2) membuat output lebih deterministik
  * Nilai yang lebih tinggi (misalnya 1,8) membuat output lebih acak

  Default: 1.0
</ParamField>

<ParamField body="max_tokens" type="integer">
  Jumlah maksimum token yang akan dibuat

  Setiap model memiliki batas maksimum yang berbeda; lihat dokumentasi model terkait
</ParamField>

<ParamField body="stream" type="boolean">
  Apakah akan menggunakan output streaming

  * `true`: Respons streaming (format SSE)
  * `false`: Mengembalikan respons lengkap sekaligus

  Default: false
</ParamField>

<ParamField body="top_p" type="number">
  Parameter nucleus sampling, rentang 0-1

  Mengontrol keragaman teks yang dihasilkan; sebaiknya digunakan sebagai alternatif temperature

  Default: 1.0
</ParamField>

<ParamField body="tools" type="array">
  Daftar tool untuk memperluas kemampuan model

  Jenis tool yang didukung:

  * **Web Search** (`web_search`): Pencarian informasi internet real-time
  * **File Search** (`file_search`): Mencari konten file yang diunggah
  * **Function Calling** (`function`): Memanggil fungsi kustom
  * **Remote MCP** (`remote_mcp`): Terhubung ke layanan Model Context Protocol jarak jauh

  Contoh: `[{"type": "web_search"}]`
</ParamField>

## Respons

<ResponseField name="id" type="string">
  Pengidentifikasi unik untuk respons
</ResponseField>

<ResponseField name="object" type="string">
  Jenis objek, tetap sebagai `response`
</ResponseField>

<ResponseField name="created" type="integer">
  Timestamp pembuatan
</ResponseField>

<ResponseField name="model" type="string">
  Nama model aktual yang digunakan
</ResponseField>

<ResponseField name="choices" type="array">
  Daftar balasan yang dihasilkan

  <Expandable title="Properti">
    <ResponseField name="index" type="integer">
      Indeks pilihan
    </ResponseField>

    <ResponseField name="message" type="object">
      Konten pesan

      <Expandable title="Properti">
        <ResponseField name="role" type="string">
          Jenis role (assistant)
        </ResponseField>

        <ResponseField name="content" type="string">
          Konten teks yang dihasilkan
        </ResponseField>
      </Expandable>
    </ResponseField>

    <ResponseField name="finish_reason" type="string">
      Alasan selesai

      Nilai yang mungkin:

      * `stop` - Selesai secara alami
      * `length` - Mencapai panjang maksimum
      * `content_filter` - Penyaringan konten
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="usage" type="object">
  Statistik penggunaan token

  <Expandable title="Properti">
    <ResponseField name="prompt_tokens" type="integer">
      Jumlah token dalam input
    </ResponseField>

    <ResponseField name="completion_tokens" type="integer">
      Jumlah token dalam output
    </ResponseField>

    <ResponseField name="total_tokens" type="integer">
      Jumlah total token
    </ResponseField>
  </Expandable>
</ResponseField>

## Contoh Penggunaan

### Input Teks Saja

```json theme={null}
{
  "model": "gpt-5.2-pro",
  "input": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Hello, introduce artificial intelligence"
        }
      ]
    }
  ]
}
```

### Menggunakan Tool Web Search

```json theme={null}
{
  "model": "gpt-5.2-pro",
  "tools": [{"type": "web_search"}],
  "input": "What positive news is there today?"
}
```

```bash cURL Example theme={null}
curl "https://api.apimart.ai/v1/responses" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer <token>" \
    -d '{
        "model": "gpt-5.2-pro",
        "tools": [{"type": "web_search"}],
        "input": "What positive news is there today?"
    }'
```

### Pemahaman Gambar

```json theme={null}
{
  "model": "gpt-5.2-pro",
  "input": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Describe this image"
        },
        {
          "type": "input_image",
          "image_url": "https://example.com/image.jpg"
        }
      ]
    }
  ]
}
```

### Analisis Multi-Gambar

```json theme={null}
{
  "model": "gpt-5.2-pro",
  "input": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Compare the similarities and differences of these two images"
        },
        {
          "type": "input_image",
          "image_url": "https://example.com/image1.jpg"
        },
        {
          "type": "input_image",
          "image_url": "https://example.com/image2.jpg"
        }
      ]
    }
  ]
}
```

### Gambar yang Dikodekan Base64

```json theme={null}
{
  "model": "gpt-5.2-pro",
  "input": [
    {
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Analyze this image"
        },
        {
          "type": "input_image",
          "image_url": "data:image/jpeg;base64,/9j/4AAQSkZJRg..."
        }
      ]
    }
  ]
}
```

### Menggunakan Tool File Search

```json theme={null}
{
  "model": "gpt-5.2-pro",
  "tools": [{"type": "file_search"}],
  "input": "Based on uploaded documents, summarize the company's quarterly performance"
}
```

### Menggunakan Function Calling

```json theme={null}
{
  "model": "gpt-5.2-pro",
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get weather information for a specified city",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {
              "type": "string",
              "description": "City name, e.g.: Beijing"
            },
            "unit": {
              "type": "string",
              "enum": ["celsius", "fahrenheit"],
              "description": "Temperature unit"
            }
          },
          "required": ["city"]
        }
      }
    }
  ],
  "input": "What's the weather like in Beijing today?"
}
```

### Menggunakan Remote MCP

```json theme={null}
{
  "model": "gpt-5.2-pro",
  "tools": [
    {
      "type": "remote_mcp",
      "remote_mcp": {
        "url": "https://mcp.example.com/api",
        "auth_token": "your_mcp_token"
      }
    }
  ],
  "input": "Query user information in the database"
}
```

### Menggabungkan Beberapa Tool

```json theme={null}
{
  "model": "gpt-5.2-pro",
  "tools": [
    {"type": "web_search"},
    {"type": "file_search"},
    {
      "type": "function",
      "function": {
        "name": "calculate",
        "description": "Perform mathematical calculations",
        "parameters": {
          "type": "object",
          "properties": {
            "expression": {
              "type": "string",
              "description": "Mathematical expression"
            }
          },
          "required": ["expression"]
        }
      }
    }
  ],
  "input": "Search for the latest Bitcoin price and calculate the total value of 100 Bitcoins"
}
```

## Spesifikasi Jenis Konten

### input\_text

Jenis input teks

**Properti:**

* `type`: Tetap sebagai `"input_text"`
* `text`: Konten teks (string)

### input\_image

Jenis input gambar

**Properti:**

* `type`: Tetap sebagai `"input_image"`
* `image_url`: URL gambar atau data URI yang dikodekan Base64

**Format gambar yang didukung:**

* JPEG
* PNG
* GIF
* WebP

**Batas ukuran gambar:**

* Ukuran file maksimum: 20MB
* `aspect_ratio` yang disarankan: tidak lebih dari 2048x2048 piksel

## Detail Penggunaan Tool

### Web Search

Tool web search memungkinkan model mengakses informasi internet real-time.

**Contoh konfigurasi:**

```json theme={null}
{
  "tools": [{"type": "web_search"}]
}
```

**Kasus penggunaan:**

* Menanyakan berita terbaru dan peristiwa terkini
* Mendapatkan data real-time (saham, cuaca, nilai tukar, dan sebagainya)
* Mencari dokumentasi teknis terbaru
* Memverifikasi informasi faktual

### File Search

Tool file search memungkinkan model mencari informasi relevan dalam dokumen yang diunggah.

**Contoh konfigurasi:**

```json theme={null}
{
  "tools": [{"type": "file_search"}]
}
```

**Kasus penggunaan:**

* Menganalisis dokumen internal perusahaan
* Mencari spesifikasi teknis dan manual
* Menanyakan kontrak dan dokumen hukum
* Sistem tanya jawab basis pengetahuan

### Function Calling

Definisikan fungsi kustom agar model dapat memanggil API eksternal atau menjalankan operasi tertentu.

**Contoh konfigurasi lengkap:**

```json theme={null}
{
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_stock_price",
        "description": "Get real-time stock price",
        "parameters": {
          "type": "object",
          "properties": {
            "symbol": {
              "type": "string",
              "description": "Stock symbol, e.g.: AAPL"
            },
            "currency": {
              "type": "string",
              "enum": ["USD", "CNY"],
              "description": "Currency unit",
              "default": "USD"
            }
          },
          "required": ["symbol"]
        }
      }
    }
  ]
}
```

**Deskripsi parameter:**

* `name`: Nama fungsi (wajib)
* `description`: Deskripsi fungsi (wajib)
* `parameters`: Definisi parameter menggunakan format JSON Schema
  * `type`: Jenis parameter
  * `properties`: Definisi properti parameter
  * `required`: Daftar parameter wajib

**Kasus penggunaan:**

* Memanggil API pihak ketiga
* Menjalankan kueri basis data
* Memicu proses bisnis
* Berintegrasi dengan sistem internal

### Remote MCP

Terhubung ke layanan Model Context Protocol (MCP) jarak jauh untuk memperluas kemampuan model.

**Contoh konfigurasi:**

```json theme={null}
{
  "tools": [
    {
      "type": "remote_mcp",
      "remote_mcp": {
        "url": "https://your-mcp-server.com/api",
        "auth_token": "your_auth_token",
        "timeout": 30
      }
    }
  ]
}
```

**Deskripsi parameter:**

* `url`: Alamat server MCP (wajib)
* `auth_token`: Token autentikasi (opsional)
* `timeout`: Timeout dalam detik, default 30 detik

**Kasus penggunaan:**

* Terhubung ke layanan AI tingkat enterprise
* Menggunakan model khusus domain
* Mengakses sumber data terlindungi
* Integrasi sistem AI terdistribusi

## Format Respons Tool

Saat model menggunakan tool, format respons akan menyertakan informasi pemanggilan tool:

```json theme={null}
{
  "id": "resp-123456",
  "object": "response",
  "created": 1677652288,
  "model": "gpt-5.2-pro",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": null,
        "tool_calls": [
          {
            "id": "call_abc123",
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"city\": \"Beijing\"}"
            }
          }
        ]
      },
      "finish_reason": "tool_calls"
    }
  ]
}
```

**Alur kerja pemanggilan tool:**

1. Model menerima input pengguna
2. Menganalisis apakah tool diperlukan
3. Jika diperlukan, mengembalikan request pemanggilan tool
4. Klien menjalankan pemanggilan tool
5. Mengembalikan hasil tool ke model
6. Model menghasilkan respons akhir

## Catatan Penting

1. **Persyaratan URL gambar**:
   * Harus berupa URL yang dapat diakses publik
   * Atau gunakan format Data URI yang dikodekan Base64

2. **Penagihan token**:
   * Gambar mengonsumsi token berdasarkan `aspect_ratio`
   * Gambar dengan `aspect_ratio` tinggi akan diubah ukurannya secara otomatis untuk mengoptimalkan biaya
   * Pemanggilan tool juga mengonsumsi token tambahan

3. **Urutan konten**:
   * Urutan elemen dalam array konten memengaruhi pemahaman model
   * Disarankan menempatkan instruksi teks terlebih dahulu, lalu gambar

4. **Kombinasi multimodal**:
   * Dapat mencampur beberapa teks dan gambar dalam satu request
   * Mendukung percakapan multi-giliran dengan koherensi konteks

5. **Batasan penggunaan tool**:
   * Saat beberapa tool digunakan sekaligus, model akan memilih tool yang paling sesuai secara cerdas
   * Function calling memerlukan definisi fungsi dan deskripsi parameter yang jelas
   * Hasil web search dapat dibatasi oleh wilayah dan waktu

6. **Kompatibilitas API**:
   * Sepenuhnya kompatibel dengan format OpenAI Responses API
   * Memigrasikan kode OpenAI yang sudah ada dengan lancar
   * Mendukung semua fitur ekstensi tool OpenAI