Chat Completions Endpoint Reference

The /v1/chat/completions endpoint conforms 100% to the OpenAI Chat Completions specification. Supported parameters include: • model (string, required): Model ID (e.g. claude-3-5-sonnet, gpt-4o, deepseek-r1). • messages (array, required): Conversational message objects with role and content. • stream (boolean, optional): Stream tokens as Server-Sent Events (SSE). Default is false. • temperature (float, optional): Sampling temperature between 0 and 2. Default is 0.7. • max_tokens (integer, optional): Maximum tokens to generate.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.apihundred.com/v1",
  apiKey: process.env.API100_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "deepseek-r1",
  messages: [
    { role: "system", content: "You are a quantitative researcher." },
    { role: "user", content: "Derive the Black-Scholes formula." }
  ],
  temperature: 0.2,
});

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