The proxy thatforgets every chat.

Private, uncensored models forJanitor AI.

Get an API key Jump to setup

Built for roleplay,
private by default

Point Janitor AI at one private endpoint, then pick any model behind it.

Browse uncensored models

Janitor AI

One proxy, the whole catalog

Janitor AI already speaks the OpenAI API, so a single proxy URL reaches every chat model here, from uncensored roleplay models to the frontier names you know.

Do you keep my chats?

Venice Role Play Uncensored

Not on the router. Your messages pass through AnonRouter in memory and are never written to disk, and on a Private route like this one the provider keeps nothing once the reply is sent.

Private

Continue the story...

No chat logs on our side

Every message is forwarded in memory and billing is settled from token counts, so there is no chat history here to leak, sell, or train on.

STEP 01

Create an API key

Sign up or sign in, open API keys, and create a key with OpenAI-compatible access ticked. Janitor AI sends the same key with every message, and that box is what lets it through. The key starts with ar_ and is shown once, so copy it before you close the dialog.

Create a key

API keysNew key

Search by name or prefix...

11 active

NameKeyUsageLimit

janitor-aiar_vhwHUTw...$4.18$10.00

sillytavernar_I5RwgEY...$2.73$5.00

fantasy-campaignar_Xr1ICrc...$1.06$3.00

risu-aiar_wGpcFAE...$0.42No limit

horror-oneshotar_sxENWfw...$0.087$1.00

slow-burnar_gv4l0DE...$0$2.00

Create API key

STEP 02

Choose your model

Start from a recommended model or search every chat model in the catalog. The config in the next step updates to match. Want more than one on hand? Import a config for each.

187 models

Recommended for roleplay

Venice Role Play UncensoredUncensoredvenice/venice-role-play-uncensoredPrivateBuilt for roleplay and long scenes, with no content filter.Privateby venice|128K context|$0.50/M input|$2.00/M outputVenice Uncensored 1.2Uncensoredvenice/venice-uncensored-1.2PrivateUnfiltered dialogue at one of the lowest prices in the catalog.Privateby venice|128K context|$0.20/M input|$0.90/M outputDeepSeek V4 Flashdeepseek/deepseek-v4-flashPrivateFast and very cheap, with a 1M token context.Privateby deepseek|via DeepInfra|1M context|$0.09/M input|$0.18/M outputKimi K2.6moonshotai/kimi-k2.6PrivateOpen weights and a 256K context for very long chats.Privateby moonshotai|256K context|$0.75/M input|$3.50/M outputClaude Sonnet 4.5anthropic/claude-sonnet-4.5AnonymousPolished, careful prose, at a higher price per message.Anonymousby anthropic|198K context|$3.75/M input|$18.75/M output

Explore hundreds more models

Where a card names a provider, its label and price are that default route; otherwise the label is the least private route a message could take. The router tries the most private route first, and a minimum privacy level in your privacy settings stops it falling back below that. Private routes keep nothing after the request; on Anonymous routes the provider sees the prompt but not who sent it.

STEP 03

Copy your config

Paste your key into the box and it drops straight into the config. Nothing is sent anywhere. Or copy the config as it is and swap in your key once it is in Janitor AI.

Your API key (optional)

Never leaves this tab. It is masked below and only goes to your clipboard.

venice-role-play-uncensored.json

{
  "name": "AnonRouter (Venice Role Play Uncensored)",
  "apiUrl": "https://api.anonrouter.ai/v1/chat/completions",
  "apiKey": "ar_REPLACE_WITH_YOUR_API_KEY",
  "model": "venice/venice-role-play-uncensored"
}

STEP 04

Import it in Janitor AI

The rest happens on Janitor AI, once per config. After the refresh, AnonRouter stays in your proxy list for every character that allows proxies.

Open any character chat
Open API Settings and pick Proxy
Under Proxy configurations, choose Import
Paste the config, then Import and SaveWant another model on hand? Pick it above and import that config too.
Refresh the pageJanitor AI only picks up a new proxy after a reload.
Choose AnonRouter and send a message

OR BY HAND

Using the + New form instead?

Same four values, one copy button each. They follow the model and key you set above.

NameAnonRouter (Venice Role Play Uncensored)

Proxy URLhttps://api.anonrouter.ai/v1/chat/completions

API KeyPaste your key in step 3

Modelvenice/venice-role-play-uncensored

Compatibility mode

Janitor AI sends the same key with every message, so these requests use the compatibility broker: the key is checked, a single-use ticket is minted in memory, and the request is forwarded with metadata-only logging. AnonRouter still logs none of your messages, but this flow is not unlinkable the way the ticket flow is. Read the docs

Why AnonRouter

Janitor AI sends the whole story. We keep none of it.

Every message carries your character, persona, and chat history to the proxy. AnonRouter forwards it in memory and settles billing from usage metadata alone.

No chat logs

Prompts and replies pass through in memory and are never written to disk. There is no chat history on our side to leak, sell, or train on.

Uncensored, and labeled

Every model in the catalog is marked uncensored, moderated, or not specified, so you know what you are getting before the scene starts.

Pay per message

Prepaid credits and no subscription. Each message is billed at the rate of the model you picked, and you can switch models whenever you like.

Troubleshooting

If a message fails

Most proxy errors come with a status code. Match it below, or read the full Janitor AI guide in the docs.

No change

Saved, but nothing changed

Refresh the Janitor AI page, reopen the chat, and pick AnonRouter as the active proxy. New proxy settings only apply after a reload.

401

Key not accepted

The key is missing, mistyped, or revoked. Paste the whole key, starting with ar_, with nothing around it.

403

Compatibility is off

This key does not have OpenAI-compatible access. Turn it on for the key in API keys, or create a new key with it ticked.

404

Wrong URL or model

The Proxy URL has to end in /v1/chat/completions. The model has to be /auto or an exact id from this page; display names do not work.

402

Out of credits

Your balance is empty. Top up from the dashboard, or switch to a cheaper model.

Blocked

No proxy option

The character's creator turned proxies off. AnonRouter counts as a proxy, so it cannot get around that.

Still stuck? Ask us on DiscordTell us the status code and the model you picked. Never post your API key there.Join our Discord

Janitor AI questions

There is no setup fee and no subscription. Messages are paid from prepaid AnonRouter credits at the rate of the model you pick, and every model's price is listed in the catalog.

Yes. Janitor AI builds every request from your character, persona, and chat history, so its own privacy terms cover that part. AnonRouter forwards the request without storing it, and the model's provider handles it according to the privacy label on the model you picked.

Private: Prompt and response content is not persistently retained after the request. Anonymous: Your identity is hidden, but the inference provider can see the prompt.

Yes, one config per model. Janitor AI takes a single model in each config, so pick a model, import its config, then pick the next and import again. Each appears as its own option under Proxy configurations, and they can all share one key. To let the router choose for you instead, search for Auto in step 2.

Auto picks an available model for each message, without quietly lowering the privacy level your account asks for. It is not in the recommended list; search for Auto in step 2 to use it. Pick a model yourself if you want every reply to come from the same one.

No. AnonRouter is an independent service and is not affiliated with Janitor AI. Janitor AI lets you bring your own proxy, and AnonRouter works as one.

Your story is not our business.

Get an API key

AnonRouter is an independent service and is not affiliated with Janitor AI.