SDKs & Libraries

Argus is fully OpenAI-compatible. Any SDK or library that supports a custom base URL works with Argus without modification.

Node.js / TypeScript

Use the official openai npm package with Argus as the base URL.

OpenAI SDK

typescript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "nxvk_your_virtual_key",
  baseURL: "https://nexus.cirruslabs.technology/v1",
});

const response = await client.chat.completions.create({
  model: "claude-sonnet-4-6",
  messages: [{ role: "user", content: "Hello!" }],
});

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

Vercel AI SDK

typescript

import { createOpenAI } from "@ai-sdk/openai";
import { generateText } from "ai";

const nexus = createOpenAI({
  apiKey: "nxvk_your_virtual_key",
  baseURL: "https://nexus.cirruslabs.technology/v1",
});

const { text } = await generateText({
  model: nexus("claude-sonnet-4-6"),
  prompt: "Hello!",
});

Python

Use the official openai Python package or any OpenAI-compatible library.

OpenAI SDK

python

from openai import OpenAI

client = OpenAI(
    api_key="nxvk_your_virtual_key",
    base_url="https://nexus.cirruslabs.technology/v1",
)

response = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Hello!"}],
)

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

LangChain

python

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="claude-sonnet-4-6",
    api_key="nxvk_your_virtual_key",
    base_url="https://nexus.cirruslabs.technology/v1",
)

response = llm.invoke("Hello!")
print(response.content)

Other Languages

Any HTTP client that can call the OpenAI API format works with Argus. Set the base URL to your Argus gateway and use a virtual key as the API key. Argus supports all OpenAI-compatible endpoints including chat completions, embeddings, and models.