API Mulai Cepat — curl, Python, TypeScript

Cara tercepat untuk memeriksa API adalah melalui curl:

Permintaan standar:

curl https://gate.joingonka.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer jg-kunci-anda" \
  -d '{
    "model": "MiniMaxAI/MiniMax-M2.7",
    "messages": [
      {"role": "user", "content": "Apa itu Gonka?"}
    ]
  }'

Streaming (respons bagian demi bagian):

curl https://gate.joingonka.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer jg-kunci-anda" \
  -d '{
    "model": "MiniMaxAI/MiniMax-M2.7",
    "messages": [
      {"role": "user", "content": "Tulis hello world dalam Python"}
    ],
    "stream": true
  }'

Respons hadir dalam format JSON (standar) atau Server-Sent Events (streaming) — sepenuhnya kompatibel dengan OpenAI API.

OpenAI Python SDK resmi bekerja dengan JoinGonka Gateway tanpa perubahan:

pip install openai

Permintaan standar:

from openai import OpenAI

client = OpenAI(
    base_url="https://gate.joingonka.ai/v1",
    api_key="jg-kunci-anda",
)

response = client.chat.completions.create(
    model="MiniMaxAI/MiniMax-M2.7",
    messages=[
        {"role": "user", "content": "Jelaskan blockchain dengan kata-kata sederhana"}
    ],
)

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

Streaming:

stream = client.chat.completions.create(
    model="MiniMaxAI/MiniMax-M2.7",
    messages=[{"role": "user", "content": "Tulis sorting di Python"}],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Tool calling:

import json

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Mendapatkan cuaca di kota",
        "parameters": {
            "type": "object",
            "properties": {
                "city": {"type": "string", "description": "Nama kota"}
            },
            "required": ["city"]
        }
    }
}]

response = client.chat.completions.create(
    model="MiniMaxAI/MiniMax-M2.7",
    messages=[{"role": "user", "content": "Bagaimana cuaca di Moskow?"}],
    tools=tools,
)

tool_call = response.choices[0].message.tool_calls[0]
print(f"Fungsi: {tool_call.function.name}")
print(f"Argumen: {tool_call.function.arguments}")

Kimi K2.6 mendukung tool calling asli — fungsi dipanggil dengan benar, tanpa perlu membedah respons teks.

Instalasi:

npm install openai

Permintaan standar:

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://gate.joingonka.ai/v1',
  apiKey: 'jg-kunci-anda',
});

async function main() {
  const response = await client.chat.completions.create({
    model: 'MiniMaxAI/MiniMax-M2.7',
    messages: [
      { role: 'user', content: 'Tulis server Express.js' },
    ],
  });

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

main();

Streaming:

const stream = await client.chat.completions.create({
  model: 'MiniMaxAI/MiniMax-M2.7',
  messages: [{ role: 'user', content: 'Jelaskan async/await' }],
  stream: true,
});

for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content || '';
  process.stdout.write(content);
}

Tool calling:

const response = await client.chat.completions.create({
  model: 'MiniMaxAI/MiniMax-M2.7',
  messages: [{ role: 'user', content: 'Konversi 100 USD ke EUR' }],
  tools: [{
    type: 'function',
    function: {
      name: 'convert_currency',
      description: 'Konversi mata uang',
      parameters: {
        type: 'object',
        properties: {
          amount: { type: 'number' },
          from: { type: 'string' },
          to: { type: 'string' },
        },
        required: ['amount', 'from', 'to'],
      },
    },
  }],
});

const toolCall = response.choices[0].message.tool_calls?.[0];
console.log(`Fungsi: ${toolCall?.function.name}`);
console.log(`Argumen: ${toolCall?.function.arguments}`);

Semua contoh menggunakan SDK OpenAI resmi — tidak diperlukan pustaka tambahan. Cukup ganti base_url dan api_key.

JoinGonka Gateway mendukung semua parameter API OpenAI Chat Completions standar:

Parameter model jaringan: jendela konteks — 200K token, respons maksimum — hingga 8192 token (untuk semua model jaringan). Daftar model tersedia melalui GET /v1/models.

Dua endpoint:

• Format OpenAI: POST https://gate.joingonka.ai/v1/chat/completions
• Format Anthropic: POST https://gate.joingonka.ai/v1/messages

Autentikasi: Authorization: Bearer jg-kunci-anda (OpenAI) atau x-api-key: jg-kunci-anda (Anthropic)

Format respons sepenuhnya kompatibel dengan OpenAI dan Anthropic — SDK, pustaka, atau framework apa pun yang mendukung API OpenAI atau Anthropic dapat bekerja dengan JoinGonka Gateway tanpa modifikasi. Claude Code terhubung melalui format Anthropic secara langsung.