プラットフォームガイド

Quick start

Go from zero to a working MoLoop API request.

How MoLoop works

MoLoop exposes models from multiple providers through one gateway. Configure the API address and key once, then change the model name when you need a different model.

API requests and Console access are separate Console sign-in manages your account. Model requests use an API key you create. Do not use a sign-in token as a model key.

API address and key

Setting	Value
BASE_URL	https://api.moloop.io/v1
API_KEY	YOUR_API_KEY

Register or sign in to MoLoop.
Open API Keys and create a key for the client you are configuring.
Open Models and pricing and copy an available model name.

Send the first request

Confirm the key and model name in the example; anonymous views show a placeholder. Keep the key only in a controlled environment.

bash

curl https://api.moloop.io/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{"model":"YOUR_MODEL_ID","messages":[{"role":"user","content":"Hello"}]}'

Use an SDK

Any SDK that accepts a custom OpenAI base URL can use the same configuration.

python

from openai import OpenAI

client = OpenAI(base_url="https://api.moloop.io/v1", api_key="YOUR_API_KEY")
response = client.chat.completions.create(
    model="YOUR_MODEL_ID",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

javascript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.moloop.io/v1",
  apiKey: "YOUR_API_KEY",
});

const response = await client.chat.completions.create({
  model: "YOUR_MODEL_ID",
  messages: [{ role: "user", content: "Hello" }],
});