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

# Chat Completions

> Kirim permintaan percakapan dengan standar OpenAI SDK dan cURL.

Endpoint `/v1/chat/completions` menyediakan kompatibilitas penuh dengan format [OpenAI](https://openai.com/?utm_source=neosantara-docs\&utm_medium=referral) API untuk penyelesaian teks, streaming token, dan pemanggilan alat.

<CodeGroup>
  ```python Python icon="python" theme={"theme":{"light":"ayu-dark","dark":"catppuccin-latte"}}
  from openai import OpenAI
  import os

  client = OpenAI(
      base_url="https://api.neosantara.xyz/v1",
      api_key=os.environ["NEOSANTARA_API_KEY"]
  )

  response = client.chat.completions.create(
      model="gemini-3.8-flash",
      messages=[
          {"role": "system", "content": "Jawab secara ringkas."},
          {"role": "user", "content": "Apa itu konsistensi data?"}
      ],
      temperature=0.7,
      max_tokens=500
  )

  print(response.choices[0].message.content)
  ```

  ```typescript TypeScript icon="js" theme={"theme":{"light":"ayu-dark","dark":"catppuccin-latte"}}
  import OpenAI from "openai";

  const client = new OpenAI({
    baseURL: "https://api.neosantara.xyz/v1",
    apiKey: process.env.NEOSANTARA_API_KEY,
  });

  const response = await client.chat.completions.create({
    model: "gemini-3.8-flash",
    messages: [
      { role: "system", content: "Jawab secara ringkas." },
      { role: "user", content: "Apa itu konsistensi data?" },
    ],
    temperature: 0.7,
  });

  console.log(response.choices[0].message.content);
  ```

  ```bash cURL icon="terminal" theme={"theme":{"light":"ayu-dark","dark":"catppuccin-latte"}}
  curl -X POST https://api.neosantara.xyz/v1/chat/completions \
    -H "Authorization: Bearer $NEOSANTARA_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gemini-3.8-flash",
      "messages": [
        {"role": "user", "content": "Apa itu konsistensi data?"}
      ]
    }'
  ```
</CodeGroup>

## Parameter Permintaan

| Parameter         | Tipe      | Default  | Deskripsi                                                                   |
| :---------------- | :-------- | :------- | :-------------------------------------------------------------------------- |
| `model`           | `string`  | Wajib    | Pengidentifikasi model (contoh: `gemini-3.8-flash`, `deepseek-v4.1-flash`). |
| `messages`        | `array`   | Wajib    | Daftar objek pesan dengan atribut `role` dan `content`.                     |
| `temperature`     | `number`  | `1.0`    | Derajat keacakan sampling (antara `0.0` hingga `2.0`).                      |
| `max_tokens`      | `integer` | Otomatis | Batas maksimum token output yang dihasilkan.                                |
| `stream`          | `boolean` | `false`  | Kirim respons secara inkremental via Server-Sent Events (SSE).              |
| `tools`           | `array`   | Opsional | Daftar fungsi yang dapat dipanggil model saat eksekusi.                     |
| `response_format` | `object`  | Opsional | Paksa output berupa objek JSON atau skema terstruktur.                      |

## Format Objek Penggunaan Token

Setiap respons yang berhasil menyertakan objek `usage` untuk kalkulasi billing Pay-As-You-Go:

```json theme={"theme":{"light":"ayu-dark","dark":"catppuccin-latte"}}
{
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 64,
    "total_tokens": 82
  }
}
```

* `prompt_tokens`: Jumlah token input yang dikirim ke gateway.
* `completion_tokens`: Jumlah token output publik yang dihasilkan model.
* `total_tokens`: Total akumulasi token input dan output.

## Fitur Lanjutan

| Fitur                      | Panduan                                                               |
| :------------------------- | :-------------------------------------------------------------------- |
| Aliran token real-time     | [Streaming Respons](/id/gateway/chat-completions/streaming)           |
| Integrasi fungsi eksternal | [Tool Calling](/id/gateway/chat-completions/tool-calling)             |
| Output JSON tervalidasi    | [Structured Outputs](/id/gateway/chat-completions/structured-outputs) |
| Model pemikiran mendalam   | [Penalaran Model](/id/gateway/chat-completions/reasoning)             |
| Input gambar multimodal    | [Vision Multimodal](/id/gateway/chat-completions/vision)              |


## Related topics

- [Streaming Respons](/id/gateway/chat-completions/streaming.md)
- [Function Calling (Tools)](/id/gateway/chat-completions/tool-calling.md)
- [Structured Outputs](/id/gateway/chat-completions/structured-outputs.md)
- [Penalaran (Reasoning)](/id/gateway/chat-completions/reasoning.md)
- [Katalog Model](/id/gateway/models.md)