The private LLM routerNo logs. No training.
Northstar Labs
Production routing and usage across the team.
This Week's Usage
View activitySpend
$11.16
Last 7 days
Requests
3,842
Last 7 days
Tokens
12.80M
Last 7 days
Workspace controls
Jump into gateway controls without exposing prompt or response content.
API Keys
Create scoped keys, review prefixes, and revoke access.
2 active
Routing
Inspect provider order, coverage, and fallback behavior.
4 providers
Privacy
Confirm no prompt, response, or secret content is retained.
payload logs off
Usage
Review request metadata, token counts, cost, and latency.
usage metadata
One router, every model, zero logs
Reach every provider through a single OpenAI-compatible endpoint: each request routed, metered, and settled from metadata, never your prompts.
Provider routing
One OpenAI-compatible endpoint routes to every model, each labeled with its privacy, pricing, and capabilities.
Labeled privacy levels
Every route is labeled with the guarantee it actually provides: Anonymous, Private, or E2EE. Filter the catalog by the privacy level you need.
Private access
No email required. Use a recovery-phrase account with opaque sessions and hashed API keys, without claiming that payment or network activity is anonymous.
Metadata metering
Every request settles from metadata: tokens, latency, status, and cost. The prompt is never stored.
Uncensored by default
Moderation is a model property, not a gateway policy. Uncensored models run unfiltered.
Privacy is the default, not a setting. AnonRouter does not persist prompts or responses in application storage or logs, and user API keys are stored only as one-way hashes. We can't train on conversations we never keep.
Three levels, clearly labeled
Every route is labeled with the guarantee it actually provides, so you can filter the catalog by the level you need.
Anonymous
Your identity is hidden from the provider, but it can see the prompt while serving the request.
Private
Prompt and response content is not retained after the request completes.
E2EE
Your client encrypts the prompt; only a verified enclave can decrypt it.
Moderation is a model property, not a gateway policy. Models published uncensored run unfiltered. Filter the catalog
Built for privacy
AnonRouter is shaped by one constraint: the gateway must never remember what you said. Getting started takes three steps.
Sign up
Create an account with an email and password, or with nothing at all. Sessions stay opaque either way.
Buy credits
Credits work across every model and provider. Spend is settled from usage metadata, never from stored prompts.
Get your API key
Mint a scoped key and start making requests with the OpenAI SDK. OpenAI-compatible Chat Completions, keys hashed at rest.
Featured models
130+ active models, one private endpoint
Chat
Talk to any text model, or run several side by side. Rooms and history live in your browser, never on the gateway.
Open chatStudio
Generate images and speech from every media model in the catalog. Results land in a library that stays on your device.
Open studio
A vibrant school of koi
A dog driving a flaming kart
Girl with a white cat
Chrome sword on 35mm filmWhat is a router?
An LLM router is one API in front of many AI models. Instead of wiring your app to each provider, you send requests to a single OpenAI-compatible endpoint and the router picks the right model, handles failures, and settles billing across providers.
AnonRouter is a private LLM router. It does all of that from usage metadata alone: prompts, responses, and keys pass through and are never written to disk. There is no request history to leak, sell, or train on, and a private account does not require an email address.
Frequently asked questions
Your prompts aren't our business.
Sign up with an email or a private recovery-phrase account, and route your first request in minutes.