LLM Proxy

Usage

Admin usage visibility without exposing secrets

Let configured administrators inspect managed users and 30-day usage without raw keys or prompts.

Operators who need oversight of managed AI access without turning dashboards into sensitive data exports.

The problem

Admin views can become dangerous if they show generated secrets, provider keys, prompts, transcripts, or model responses.

How LLM Proxy helps

LLM Proxy exposes admin-only user and usage summaries while explicitly excluding provider API keys, masked key strings, generated secrets, secret digests, prompts, responses, audio names, and transcripts.

How it works

  1. Configure administrator emails in management.admin_emails.
  2. Authenticate through TAuth with a matching email.
  3. Open the Admin item from the avatar menu.
  4. Review tenant facts and 30-day usage summaries for managed users.

Feature-to-benefit table

Feature Why it matters here Example
Config-owned admins Admin status comes from validated TAuth email and config. There is no hidden browser-only admin toggle.
Admin API GET /api/management/admin/users returns managed user and usage facts. Non-admin sessions receive 403.
No secret leakage Admin responses omit raw and masked provider keys plus generated secrets. Oversight stays operational.

Use-case examples

Support triage

An admin checks whether a user has a tenant secret and recent usage before asking for logs.

Traffic review

An operator reviews user-level request counts and token totals.

Access check

A non-admin user cannot call the admin endpoint successfully.

Objections and limitations

  • Admin emails must be configured exactly in runtime config.
  • The admin dashboard summarizes usage; it does not expose prompt content.
  • The API depends on valid TAuth session cookies.

FAQ

What is the main job of admin usage visibility without secrets?

LLM Proxy exposes admin-only user and usage summaries while explicitly excluding provider API keys, masked key strings, generated secrets, secret digests, prompts, responses, audio names, and transcripts.

Who should read this usage resource?

Operators who need oversight of managed AI access without turning dashboards into sensitive data exports.

Does this page claim provider performance or pricing advantages?

No. The supported claim is about LLM Proxy's documented routing, configuration, management, security, usage, and deployment contracts. Provider cost, speed, rankings, and benchmark claims are not made here.

Where should setup details come from?

Use the main README and implementation notes for current command, config, and endpoint details. This page summarizes the workflow without replacing LLM Proxy documentation.

What should I read next?

A closely related resource is Normalized token usage metadata across providers, which covers normalized token usage metadata.

Related resources

Use this pattern in LLM Proxy

Start from the canonical API reference, then use the management surface when the workflow needs tenant or provider configuration.

Open API reference