OpenAI SDKs

Both work with Laras Router once you change the base URL and the key. Every step was checked against the SDKs’ own documentation.

You need an API key (lr_live_…) and a topped-up balance. New to Laras Router? Start with the Quickstart.

Python

The official OpenAI library for Python.

pip install openai

export LARAS_API_KEY="lr_live_your_key_here"

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.larasrouter.com/v1",
    api_key=os.environ["LARAS_API_KEY"],
)

completion = client.chat.completions.create(
    model="deepseek-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(completion.choices[0].message.content)

Good to know

• Use client.chat.completions.create. The SDK’s README leads with the Responses API (client.responses.create), which Laras Router does not implement.
• For streaming, pass stream=True. The SDK also reads OPENAI_BASE_URL and OPENAI_API_KEY if you prefer environment variables to arguments.

Node.js

The official OpenAI library for Node.js and TypeScript.

npm install openai

export LARAS_API_KEY="lr_live_your_key_here"

import OpenAI from "openai";

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

const completion = await client.chat.completions.create({
  model: "deepseek-flash",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);

Good to know

• Use client.chat.completions.create. The SDK’s README leads with the Responses API (client.responses.create), which Laras Router does not implement.
• The example uses top-level await, so run it as an ES module (an .mjs file or a package with "type": "module").

Settings and screens can change between versions. If something looks different, check the OpenAI Python SDK documentation or the OpenAI Node SDK documentation. For other tools, see all integrations.