Private launch

Prepare your integration.

PENGYU is preparing an Indonesia-first private launch. Production access, enabled models and the final endpoint will be issued only when the console is ready.

Public accounts, production endpoints, model availability and pricing are not open yet.

1. Review the launch flow

Read the integration guidance now. Account registration and API token issuance will open only after the production console is ready.

View launch notes

2. Prepare your client

Do not hardcode a temporary or local server address. Set the production HTTPS endpoint only after it is issued to your account.

Environment variable

PENGYU_BASE_URL=ISSUED_BY_PENGYU

3. Keep credentials server-side

When private-launch access opens, use the model list endpoint to verify the token from your server. Never place a production token in client-side code.

cURL

curl "$PENGYU_BASE_URL/models" \
  -H "Authorization: Bearer YOUR_API_TOKEN"

4. Keep your request portable

Replace the placeholder token and model only with values issued through your production console. The model name must match an enabled model.

Python

import os

from openai import OpenAI

client = OpenAI(
    base_url=os.environ["PENGYU_BASE_URL"],
    api_key="YOUR_API_TOKEN",
)

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

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

No public endpoint, model, pricing or service status is published during pre-launch. Use only values shown in your verified console after access opens.

Before access opens

Keep future API tokens in server-side environment variables.
Wait for the verified production endpoint, models and limits.
Use the production HTTPS console domain only after it is configured.