API Mulai Cepat — curl, Python, TypeScript

Cara tercepat untuk menguji API adalah dengan curl:

Permintaan biasa:

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

Streaming (respons bertahap):

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

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

SDK Python resmi OpenAI langsung bekerja dengan JoinGonka Gateway tanpa perubahan apa pun:

pip install openai

Permintaan biasa:

from openai import OpenAI

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

response = client.chat.completions.create(
    model="MiniMaxAI/MiniMax-M2.7",
    messages=[
        {"role": "user", "content": "Explain blockchain in simple terms"}
    ],
)

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

Streaming:

stream = client.chat.completions.create(
    model="MiniMaxAI/MiniMax-M2.7",
    messages=[{"role": "user", "content": "Write a sorting function in 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": "Get the weather in a city",
        "parameters": {
            "type": "object",
            "properties": {
                "city": {"type": "string", "description": "City name"}
            },
            "required": ["city"]
        }
    }
}]

response = client.chat.completions.create(
    model="MiniMaxAI/MiniMax-M2.7",
    messages=[{"role": "user", "content": "What is the weather in Moscow?"}],
    tools=tools,
)

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

Model-model di jaringan ini mendukung tool calling native — fungsi dipanggil dengan benar, tanpa perlu parsing respons teks.

Instalasi:

npm install openai

Permintaan biasa:

import OpenAI from 'openai';

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

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

  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: 'Explain 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: 'Convert 100 USD to EUR' }],
  tools: [{
    type: 'function',
    function: {
      name: 'convert_currency',
      description: 'Currency conversion',
      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(`Function: ${toolCall?.function.name}`);
console.log(`Arguments: ${toolCall?.function.arguments}`);

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

JoinGonka Gateway mendukung semua parameter standar OpenAI Chat Completions API:

Parameter model jaringan: jendela konteks — 200K token pada MiniMax M2.7 (380K pada DeepSeek V4 Flash, 390K pada GLM-5.3 Flash), respons maksimum — hingga 8192 token (pada DeepSeek V4 Flash — hingga 32768). 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-your-key (OpenAI) atau x-api-key: jg-your-key (Anthropic)

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