Documentation

TypeScript quickstart

Integrate Meridian into your TypeScript application in under five minutes. ESM-first, fully typed, with streaming and tool-calling support.

← All docsAPI reference

Install

npm i openai

Meridian is compatible with the OpenAI Node.js SDK. Point the baseURL at our endpoint and use your API key.

Basic ESM example

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.getnimbus.net/v1",
  apiKey: process.env.MERIDIAN_API_KEY!,
});

const completion = await client.chat.completions.create({
  model: "meridian-1",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Explain ECC memory in two sentences." },
  ],
});

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

Streaming

const stream = await client.chat.completions.create({
  model: "meridian-1",
  messages: [{ role: "user", content: "Write a haiku about Rust." }],
  stream: true,
});

for await (const chunk of stream) {
  const delta = chunk.choices[0]?.delta?.content;
  if (delta) process.stdout.write(delta);
}

Tool calling

const tools = [
  {
    type: "function" as const,
    function: {
      name: "get_weather",
      description: "Get current temperature for a city",
      parameters: {
        type: "object",
        properties: {
          city: { type: "string" },
        },
        required: ["city"],
      },
    },
  },
];

const response = await client.chat.completions.create({
  model: "meridian-1",
  messages: [{ role: "user", content: "What's the weather in Oslo?" }],
  tools,
  tool_choice: "auto",
});

const toolCall = response.choices[0]?.message?.tool_calls?.[0];
if (toolCall) {
  const args = JSON.parse(toolCall.function.arguments);
  console.log("Tool called:", toolCall.function.name, args);
}

Next steps