Quickstart

Prerequisites

Before getting started, ensure you have the following:

• An API key for your inference service
• curl installed, or alternatively Python or Node.js if you plan to use an SDK

Step 1: Generate and export your API key

Save your API key in an environment variable rather than embedding it directly in your source code.

cURL

export INFERENCE_BASE_URL="https://api.rygen.io/v1"
export INFERENCE_API_KEY="your_api_key_here"
export INFERENCE_MODEL="minimax/minimax-m2.5"

Step 2: Send your first API request

Use your API key and selected model to make your initial call to the inference service.

cURL

curl --request POST \
  --url "$INFERENCE_BASE_URL/chat/completions" \
  --header "Authorization: Bearer $INFERENCE_API_KEY" \
  --header "Content-Type: application/json" \
  --data @- <<EOF
{
  "model": "${INFERENCE_MODEL}",
  "messages": [
    {
      "role": "user",
      "content": "Hello, How are you doing?"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 128
}
EOF

A successful response usually looks like this:

JSON

{
  "id": "160fc64c758b420e938644613a8d1a1c",
  "object": "chat.completion",
  "created": 1776012472,
  "model": "minimax/minimax-m2.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I'm doing well, thank you for asking! How can I help you today?",
        "reasoning_content": "The user is asking how I am. This is a casual greeting/check-in. I should respond in a friendly, conversational way.\n",
        "tool_calls": null
      },
      "logprobs": null,
      "finish_reason": "stop",
      "matched_stop": 200020
    }
  ],
  "usage": {
    "prompt_tokens": 42,
    "total_tokens": 87,
    "completion_tokens": 45,
    "prompt_tokens_details": {
      "cached_tokens": 41
    },
    "reasoning_tokens": 0
  },
  "metadata": {
    "weight_version": "default"
  }
}

---

Python with OpenAI SDK

First, Install the SDK:

cURL

pip install openai

Next, send a request to your service using your configured API key and model:

Python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["INFERENCE_API_KEY"], base_url=os.environ["INFERENCE_BASE_URL"],)

response = client.chat.completions.create(
    model=os.environ["INFERENCE_MODEL"],
    messages=[
        {"role": "user", "content": "Hello, How are you doing?"}
    ],
    temperature=0.7,
    max_tokens=128,
)

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

---

JavaScript / TypeScript with OpenAI SDK

First, Install the SDK:

cURL

npm install openai

Next, send a request to your service using your configured API key and model:

TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.INFERENCE_API_KEY,
  baseURL: process.env.INFERENCE_BASE_URL,
});

const response = await client.chat.completions.create({
  model: process.env.INFERENCE_MODEL,
  messages: [
    {
      role: "user",
      content: "Hello, How are you doing?",
    },
  ],
  temperature: 0.7,
  max_tokens: 128,
});

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