Quickstart

OpenToken implements the OpenAI Chat Completions API. Change only the base URL and the API key, then call any registered model using the {provider}/{model} id format.

Create an API key

In the console, open a workspace and create a server-side key. Keys start with sk-optk- and the secret is shown only once.

Point the SDK at OpenToken

Set the client base URL to https://api.opentoken.kr/v1 and use your OpenToken key as the API key.

Send your first request

from openai import OpenAI

client = OpenAI(
    base_url="https://api.opentoken.kr/v1",
    api_key="sk-optk-...",
)

resp = client.chat.completions.create(
    model="google/gemini-3-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.opentoken.kr/v1",
  apiKey: process.env.OPENTOKEN_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "google/gemini-3-flash",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(resp.choices[0].message.content);

curl https://api.opentoken.kr/v1/chat/completions \
  -H "Authorization: Bearer $OPENTOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3-flash",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

Model ids use the {provider}/{model} format. Call GET /v1/models to list what is registered — see Models.

Next steps

Streaming

Receive tokens as Server-Sent Events.

Reasoning

Control thinking depth per request.

API reference

Full chat completion parameters.