API Mabilis na Pagsisimula — curl, Python, TypeScript

Ang pinakamabilis na paraan para subukan ang API — curl:

Karaniwang request:

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 (pira-pirasong sagot):

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
  }'

Dumarating ang sagot sa JSON (karaniwan) o Server-Sent Events (streaming) — ganap na compatible sa OpenAI API.

Gumagana ang opisyal na OpenAI Python SDK sa JoinGonka Gateway nang walang anumang pagbabago:

pip install openai

Karaniwang request:

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}")

Sinusuportahan ng mga modelo ng network ang native na tool calling — tama ang pagtawag sa mga function, walang kailangang i-parse na text response.

Pag-install:

npm install openai

Karaniwang request:

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}`);

Gumagamit ang lahat ng halimbawa ng opisyal na OpenAI SDK — walang kailangang karagdagang library. Palitan lang ang base_url at api_key.

Sinusuportahan ng JoinGonka Gateway ang lahat ng karaniwang parameter ng OpenAI Chat Completions API:

Mga parameter ng mga modelo sa network: context window — 200K token sa MiniMax M2.7 (380K sa DeepSeek V4 Flash, 390K sa GLM-5.3 Flash), pinakamahabang sagot — hanggang 8192 token (sa DeepSeek V4 Flash — hanggang 32768). Available ang listahan ng mga modelo sa pamamagitan ng GET /v1/models.

Dalawang endpoint:

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

Authentication: Authorization: Bearer jg-your-key (OpenAI) o x-api-key: jg-your-key (Anthropic)

Ang format ng sagot ay ganap na compatible sa OpenAI at Anthropic — anumang SDK, library, o framework na sumusuporta sa OpenAI o Anthropic API ay gumagana sa JoinGonka Gateway nang walang pagbabago. Ang Claude Code ay direktang kumokonekta sa pamamagitan ng Anthropic-format.