Getting Started
Set up your workspace and deploy your first AI model in under 5 minutes.
Get from zero to a working AI model with an API endpoint in 4 steps.
Prerequisites: A UnieAI Studio account. Sign up here if you don't have one.
Sign in to your account
UnieAI Studio currently supports the following sign-in methods:
Select Sign in with Google on the login page and continue with your Google account. No separate registration is required.
Select Sign in with Microsoft to use your organization's Microsoft Entra ID／Azure Active Directory account. This option is suitable for organizations using Microsoft 365.
Test accounts are created by platform administrators specifically for development and QA workflows. Ask your administrator for the account name and password first.
The Sign in with test account button appears on the login page only when the platform has at least one test account. Select it, enter the account name (for example, testuser01) and password in the dialog, and then select Sign in. The system automatically maps the account name to testuser01@test_account.com; do not enter the full email address yourself.
Test accounts are intended only for development, demonstrations, or QA verification. Production users should sign in with Google, Microsoft／Azure AD, or their organization's SSO.
Quick Start
Create a Customize Model
From the sidebar, go to Marketplace > UnieAI Model Zoo and browse the available base models.
- Open the model you want and select Use base model.
- In the confirmation dialog, select Add to my models. When Model connected appears, select Close.
- From the sidebar, go to My assets > My models.
- Select Create custom model in the upper-right corner.
- Choose a Base model and enter a Display name.
- Select Create Customize Model.
After the Customize Model is created, you can continue configuring its behavior, data sources, and API integration.
Get Your API Key
From the sidebar, go to Workspace > API keys and select Create key. In the Create API key dialog, enter a Key name and optionally configure an expiry, rate limits, or quota. Select Generate, then select Copy secret in the secret dialog.
The full secret is shown only once. Copy it immediately, store it securely, and never commit it to version control or share it publicly.
Make Your First API Call
Use any OpenAI-compatible SDK or plain HTTP:
curl https://your-studio.example.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "my-custom-model",
"messages": [
{"role": "user", "content": "Hello! What can you do?"}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://your-studio.example.com/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="my-custom-model",
messages=[{"role": "user", "content": "Hello! What can you do?"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://your-studio.example.com/v1",
apiKey: "YOUR_API_KEY",
});
const response = await client.chat.completions.create({
model: "my-custom-model",
messages: [{ role: "user", content: "Hello! What can you do?" }],
});
console.log(response.choices[0].message.content);What's Next?
Add a Knowledge Base
Upload documents so your model can answer questions with real data.
Enable Agent Mode
Give your model tools and let it handle multi-step tasks.
Set Up Guardrails
Add content safety filters to protect your users.
API Reference
Full endpoint documentation with examples.