Skip to main content

Getting Started with TokenVue

TokenVue helps you manage LLM access through secure virtual keys, provider configuration, guardrails, routing, and usage monitoring.

This guide walks through the basic setup path.

1. Sign In to TokenVue​

Open TokenVue and sign in to your workspace.

After login, you land in the TokenVue dashboard, where you can review usage, active keys, provider activity, guardrail events, and workspace-level insights.

2. Create or Select a Workspace​

A workspace is where your team manages LLM access.

Inside a workspace, you can manage:

  • Virtual keys
  • LLM provider configurations
  • Guardrails
  • Usage logs
  • Billing visibility
  • Team access

Select an existing workspace or create a new one before configuring your gateway.

3. Configure an LLM Provider​

Go to LLM Config and add the provider TokenVue should route requests to.

You can configure details such as:

  • Provider name
  • API key
  • Base URL, if using an OpenAI-compatible provider
  • Model name
  • Budget mode
  • Token or request limits

TokenVue uses this configuration when routing requests through the gateway.

4. Create a Virtual Key​

Go to Virtual Key and create a new gateway key.

A virtual key is the key your application uses instead of directly using the provider API key.

Virtual keys let you control:

  • Which model or provider is used
  • Monthly or daily limits
  • Token-based limits
  • Guardrail behavior
  • Service ownership
  • Usage tracking

After creating a key, TokenVue generates an OpenAI-compatible API key for your application.

5. Connect Your Application​

Use the TokenVue gateway as an OpenAI-compatible API endpoint.

curl -X POST "https://your-tokenvue-domain.com/v1/chat/completions" \
  -H "Authorization: Bearer sk-tg-live-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "configured-model",
    "messages": [
      {
        "role": "user",
        "content": "Hello from TokenVue"
      }
    ]
  }'

For local development, the base URL may look like this:

http://localhost:3000/v1

6. Enable Guardrails​

Go to Guardrails to manage workspace-level protections.

TokenVue supports guardrails such as:

  • Hard budget caps
  • PII scrubbing
  • Toxicity filtering
  • Prompt injection detection
  • Keyword blocking

These guardrails help protect your workspace before requests are sent to an LLM provider.

7. Review Logs and Insights​

After traffic starts flowing through TokenVue, use Logs, Breaches, and Insights to review activity.

You can monitor:

  • Token usage
  • Request status
  • Provider latency
  • Model routing behavior
  • Blocked requests
  • Failed requests
  • Security-related events

Next Steps​

Once your first virtual key is working, continue with:

TokenVue is now ready to manage and monitor your LLM gateway traffic.