Skip to main content

OpenAI SDK

Use the official OpenAI SDK (Python / JavaScript) to call this OpenAI-compatible inference service. This page only covers SDK configuration for the HPC-AI inference endpoint. For request fields and feature usage, refer to the API reference and user guides linked below.

Endpoint & Authentication​

Point the SDK client to the HPC-AI inference base URL and pass your API key:

  • Base URL: https://api.hpc-ai.com/inference/v1
  • Authentication: Authorization: Bearer <your_api_key>

Installation​

Python​

pip install openai

JavaScript / TypeScript​

npm install openai

Keep secrets out of source code by using environment variables:

export INFERENCE_BASE_URL="https://api.hpc-ai.com/inference/v1"
export INFERENCE_API_KEY="your_api_key_here"
export INFERENCE_MODEL="minimax/minimax-m2.5"

Minimal Example​

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": "Say hello in one short sentence."}
    ],
)

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

JavaScript / 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: "Say hello in one short sentence." },
  ],
});

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