Product-User Quickstart

In Zorveus, Product Users represent your application's end users. Instead of building complex usage-tracking databases, you pass your customer's ID directly in the inference request metadata.

Inline Product-User Creation

When Zorveus processes an inference request containing an external_user_id it has not seen before, it automatically creates the product user inline in your startup workspace.

Subsequent requests with the same external_user_id update the product user's metadata (e.g. name, email, plan) and aggregate usage seamlessly.

Send Request with User Attribution

Add the user parameter or extra_body.metadata to your standard OpenAI client call:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.zorveus.com/v1",
    api_key="zrv_your_inference_key",
)

response = client.chat.completions.create(
    model="openai/gpt-4.1-mini",
    messages=[
        {"role": "user", "content": "Summarize the latest trends in renewable energy."}
    ],
    # Pass Zorveus product-user metadata
    extra_body={
        "metadata": {
            "external_user_id": "usr_cust_94821",
            "name": "Sarah Connor",
            "email": "sarah.connor@example.com",
            "plan": "pro_tier",
            "team_id": "team_alpha",
        }
    },
)

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

Identifier Resolution Precedence

When attributing requests to product users, Zorveus applies the following hierarchy:

1. external_user_id (Recommended): Your own database primary key (e.g. usr_98124, auth0|123456). Zorveus indexes and resolves this immediately.
2. product_user_id: An internal Zorveus UUID if you previously fetched or created the product user via the Management API.
3. OpenAI user field: If metadata.external_user_id is omitted, Zorveus falls back to the standard OpenAI top-level user string as the external_user_id.

Observing Product Users in Dashboard

After making the request:

1. Go to app.zorveus.com -> Product Users.
2. Search for usr_cust_94821 or Sarah Connor.
3. View the customer's:
   • Lifetime token consumption and requests
   • Remaining credit balance (if credit grants are applied)
   • Spending caps and active rate limits
   • Full timeline of AI requests

Next Steps