anonrouter
Sign up

The endpoint thatforgets every chat.

Private, uncensored models forSillyTavern.

Get an API keyJump to setup

Setup walkthrough

Video coming soon

Built for roleplay,
private by default

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

SillyTavern
VeniceDeepSeekKimiClaudeGemini

One endpoint, the whole catalog

SillyTavern already speaks the OpenAI API, so one endpoint and one key reach every chat model here, from uncensored roleplay models to the frontier names you know.

Do you keep my chats?

VeniceVenice 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. Your history stays in SillyTavern.

PrivateVenice
Continue the story...

No chat logs on our side

Every message is forwarded in memory and billing is settled from token counts. Your chat history stays in SillyTavern, on the machine that runs it.

STEP 01

Create an API key

Sign up or sign in, open API keys, and create a key with OpenAI-compatible access ticked. SillyTavern 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
NameUsageLimit
sillytavern$2.73$5.00
janitor-ai$4.18$10.00
fantasy-campaign$1.06$3.00
risu-ai$0.42No limit
horror-oneshot$0.087$1.00
slow-burn$0$2.00

API

API

Chat Completion

Chat Completion Source

Custom (OpenAI-compatible)

Custom Endpoint (Base URL)

https://api.anonrouter.ai/v1

Create API key

STEP 02

Choose your model

Start from a recommended model or search every chat model in the catalog. Its id fills the Model ID in the next step, and SillyTavern lists every model too once you connect.

187 models

Recommended for roleplay

Model
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 connection details

Paste your key into the box and it drops into the details below. Nothing is sent anywhere. Then copy each value into the field of the same name in SillyTavern.

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

API Connections

  • API

    Chat Completion

    Select

  • Chat Completion Source

    Custom (OpenAI-compatible)

    Select

  • Custom Endpoint (Base URL)

    https://api.anonrouter.ai/v1

  • Custom API Key

    ar_REPLACE_WITH_YOUR_API_KEY

  • Enter a Model ID

    venice/venice-role-play-uncensored

STEP 04

Connect in SillyTavern

The rest happens in SillyTavern's API Connections panel. Once Test Message answers, every character chat runs through AnonRouter.

  1. Open API Connections, the plug icon in the top bar
  2. Set API to Chat Completion
  3. Set Chat Completion Source to Custom (OpenAI-compatible)
  4. Paste the endpoint, your key, and the model IDNo slash at the end of the endpoint: SillyTavern adds /chat/completions itself.
  5. Click Connect, then Test MessageIt sends a quick hello and should report API connection successful.
  6. Open a character and start chattingSave the setup as a Connection Profile to switch models later.
Compatibility mode

SillyTavern 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

SillyTavern sends the whole story. We keep none of it.

Every message carries your character card, persona, lorebook entries, and chat history. 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 connection errors come with a status code. Match it below, or read the full SillyTavern guide in the docs.

401

Key not accepted

The key is missing, mistyped, or revoked. Paste the whole key, starting with ar_, into Custom API Key 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 endpoint or model

The endpoint is https://api.anonrouter.ai/v1, with no slash at the end; SillyTavern adds /chat/completions itself. The model has to be /auto or an exact id from this page, and API has to be Chat Completion, not Text Completion.

Empty list

No models to pick

Check the endpoint, key, and compatibility, then Connect again. You can also type the id into Enter a Model ID; chat works without the list.

400

Request rejected

Clear Additional Parameters and try a plain text chat. Image messages and more than one reply per message are not supported.

402

Out of credits

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

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

SillyTavern 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.
In SillyTavern's own data folder (data/default-user/chats), on the machine that runs it; if you host SillyTavern on a server, that server holds them. AnonRouter keeps none of what it forwards, and the model's provider handles each message according to the privacy label on the model you picked.
In SillyTavern's secrets.json (data/default-user/secrets.json by default), unencrypted. SillyTavern hides it on screen after you connect, but anyone who can read that folder can use the key, so keep the machine and its SillyTavern server private.
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. Pick another model from Available Models whenever you like, or save each one as a Connection Profile and switch between them. They all share one key.
Auto picks an available model for each message, without quietly lowering the privacy level your account asks for. Enter /auto as the Model ID to use it; pick a model yourself if you want every reply to come from the same one.
Chat Completion. AnonRouter speaks the chat format; Text Completion calls an older endpoint it does not have, so it fails.
No. AnonRouter is an independent service and is not affiliated with SillyTavern. SillyTavern works with any OpenAI-compatible API, and AnonRouter is one.

Your story is not our business.

Get an API key

AnonRouter is an independent service and is not affiliated with SillyTavern.

SillyTavern API setup: private roleplay with AnonRouter