A practical guide to choosing a Janitor AI proxy, finding a model that suits your chats, and getting it connected.

WHAT MAKES A GOOD PROXY?

A good proxy should give you fast replies, strong roleplay models, and control over what happens to your chats.

AnonRouter is my top pick for privacy-focused roleplay. It brings uncensored models, fast options like DeepSeek Flash, and a broad model catalog into one setup. You can create an account without an email address, switch models without juggling provider accounts, and pay as you go. AnonRouter does not log or retain your prompts or responses, so your conversations aren’t being saved or used for training.

Here’s how to connect it.

1. GET YOUR API KEY

Go to https://anonrouter.ai and create an account.

Open API Keys in the dashboard and create an inference key. Make sure OpenAI-compatible access is enabled.

Copy the key when it appears. It begins with ar_ and is shown only once.

2. OPEN JANITOR’S PROXY SETTINGS

Open a character chat.

Go to API Settings → Proxy → Proxy configurations → Import.

The character must allow third-party proxies.

3. IMPORT THIS CONFIGURATION

Replace the example API key with your own before importing:

{

"name": "My Proxy",

"apiUrl": "https://api.anonrouter.ai/v1/chat/completions",

"apiKey": "ar_REPLACE_WITH_YOUR_API_KEY",

"model": "mistralai/mistral-uncensored-1.2"

}

Prefer manual setup? Choose + New and enter:

Name: My Proxy

Proxy URL: https://api.anonrouter.ai/v1/chat/completions

API Key: your AnonRouter key

Model: /auto

Keep the full URL, including /chat/completions.

4. SAVE AND REFRESH

Save the API settings, refresh Janitor AI, and select My Proxy as your active configuration.

Send a short test message to check that it responds.

5. CHOOSE YOUR MODEL

Use /auto to let the router choose an eligible model.

To keep your chats on one model, replace /auto with an exact model ID from:

https://anonrouter.ai/models

Check its price, context limit, and capabilities. For uncensored models, use the catalog’s filter. Moderation and privacy are separate properties, so check both labels.

You can create separate proxy configurations for different models. Give each a recognizable name so you can switch between them.

TROUBLESHOOTING

Configuration saved but nothing changed:

Refresh Janitor AI and select the intended proxy.

401:

Check that your API key is complete, has no extra spaces, and has not been revoked.

403 / compat_scope_required:

Enable OpenAI-compatible access for the key in your dashboard.

404:

Check the full endpoint. Do not stop at /v1 or add /chat/completions twice.

Model not found:

Use /auto or copy the exact current chat-model ID from the catalog.

429:

Wait before retrying and check your account’s usage limits.

Insufficient credits:

Check your balance. Changing models will not fix an empty balance.

No proxy option:

The character creator may have disabled proxies.

PRIVACY

Keep API keys out of comments and screenshots.

MORE HELP

Setup page:

https://anonrouter.ai/janitor-ai

Detailed documentation:

https://docs.anonrouter.ai/janitor-ai