Integration Guide

Connect MultiConnection to your AI tools

One MultiConnection API key works with clients, scripts and SDKs that support OpenAI-compatible endpoints. Create a key, replace the base URL, and start testing.

Create API Key Read API Docs
Base URL https://multiconnection.cloud/v1
Authorization Bearer sk-live-...
Recommended test model gpt-5.4-mini
Quick Start

Complete integration in four steps

1. Register

Create an account in the console with email and password. New accounts can receive a small test balance.

2. Create an API key

Create a key on the API Keys page. The secret is shown only once, so copy it immediately.

3. Configure your client

Select OpenAI-compatible or custom OpenAI endpoint, then paste the MultiConnection base URL and key.

4. Send a test request

Start with a lightweight model, then switch to Claude, GPT, DeepSeek or other routes for your workload.

Clients

Common client setup

Cursor / IDE tools

Choose OpenAI-compatible, custom OpenAI or third-party API in the model/provider settings.

  • Base URL: https://multiconnection.cloud/v1
  • API Key: the sk-live-... key from the console
  • Model: gpt-5.4-mini or claude-sonnet-4.6

Cline / Roo Code

Select OpenAI Compatible as the provider and enter the MultiConnection endpoint and model code.

  • API Provider: OpenAI Compatible
  • Base URL: https://multiconnection.cloud/v1
  • Model ID: copy a model code from the console pricing table

Cherry Studio

Add a custom provider and choose OpenAI-compatible mode.

  • Provider name: MultiConnection
  • API endpoint: https://multiconnection.cloud/v1
  • Secret: your console API key

Codex note

A MultiConnection API key cannot sign in to a Codex account. It works only when the client supports a custom OpenAI-compatible base URL.

  • Start with /v1/chat/completions
  • Codex-specific routes such as /v1/responses can be added as a separate compatibility layer
SDK

OpenAI SDK examples

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.MULTICONNECTION_API_KEY,
  baseURL: "https://multiconnection.cloud/v1"
});

const result = await client.chat.completions.create({
  model: "gpt-5.4-mini",
  messages: [{ role: "user", content: "hello MultiConnection" }]
});

Python

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["MULTICONNECTION_API_KEY"],
    base_url="https://multiconnection.cloud/v1",
)

result = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[{"role": "user", "content": "hello MultiConnection"}],
)
Models

Model selection guide

gpt-5.4-miniDefault testing, general chat, lightweight agents
claude-sonnet-4.6Code, long context and complex reasoning
deepseek-v4-flashCost-effective calls and batch workloads
seedance-2.0-fastVideo generation testing