Skip to content
PleumRouter

Quickstart

Use the currently listed supported models through an OpenAI-compatible API, billed in KRW. Start by setting base_url.

Setting up with an AI assistant (ChatGPT, Claude, Cursor)? Grab a copy-paste snippet (Markdown/JSON) from Set up with AI and paste it to your AI — that's it.

Get started in 3 steps#

  1. 1

    Create an account

    Sign up with email.

  2. 2

    Top up credits

    Add credits under Dashboard → Billing (minimum ₩5,000).

  3. 3

    Issue an API key

    Create a key starting with plm_ under Dashboard → API Keys and paste it into the code below.

Python (OpenAI SDK)#

You can use the OpenAI SDK with documented compatible endpoints. Set api_key and base_url, then check model-specific supported features.

quickstart.py
from openai import OpenAI

client = OpenAI(
    api_key="plm_xxxxxxxxxxxxxxxx",   # PleumRouter API key
    base_url="https://apirouter.pleum.ai/v1",
)

response = client.chat.completions.create(
    model="gpt-4.1",
    messages=[{"role": "user", "content": "Hello"}],
)

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

TypeScript / JavaScript#

quickstart.ts
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "plm_xxxxxxxxxxxxxxxx",
  baseURL: "https://apirouter.pleum.ai/v1",
});

const messages: OpenAI.ChatCompletionMessageParam[] = [
  { role: "user", content: "Hello" },
];

const response: OpenAI.ChatCompletion = await client.chat.completions.create({
  model: "gpt-4.1",
  messages,
});

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

cURL#

terminal
curl https://apirouter.pleum.ai/v1/chat/completions \
  -H "Authorization: Bearer plm_xxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
The cost field in the response shows this call's cost in KRW, the applied FX rate, and markup. For the full response format, see the Chat Completions reference.

Next steps#