Skip to content

DevelopersDeveloper platform

DocsChatConsole

IntegrationsSillyTavern

Connect SillyTavern to Unrestricted AI

Use Unrestricted AI as a Custom (OpenAI-compatible) Chat Completion source in SillyTavern. Base URL, API key and model ID in under a minute.

Get your key
Custom Endpoint (Base URL)
https://tryunrestrictedai.com/v1
Base URL. SillyTavern adds /chat/completions.
Model ID
venice-uncensored-1-2
Type it exactly.
API keyCreate a key in the consoleStarts with ua_. Shown once, so save it.

Set up SillyTavern

  1. Open API Connections

    Click the plug icon in the top bar of SillyTavern.

  2. Set API to “Chat Completion”

  3. Set Chat Completion Source to “Custom (OpenAI-compatible)”

  4. Paste the base URL into “Custom Endpoint (Base URL)”

    Use the base URL only. SillyTavern adds /chat/completions itself.

    https://tryunrestrictedai.com/v1

  5. Paste your key into “Custom API Key”

    The key starts with ua_. Paste it without the word Bearer.

    Get your key

  6. Pick the model

    Choose it from Available Models after connecting, or type the model ID into “Enter a Model ID”.

    venice-uncensored-1-2

  7. Click “Connect”, then “Test Message”

    A green status dot and a reply to the test message mean you are connected.

Recommended settings

  • Output limit: 4,096 tokens. Context window: 32,768 tokens.
  • In AI Response Configuration, keep “Max Response Length (tokens)” at or below the output limit above.
  • Keep “Multiple swipes per generation” at 1. Each swipe is a separate request.
  • Labels can shift slightly between SillyTavern releases; the Custom (OpenAI-compatible) source is the one to use.
  • Text chat with streaming is supported. Image input, tool calling and multiple completions per request (n > 1) are not.

Troubleshooting

Your app shows the HTTP status and usually our error code. Match it here.

401invalid_api_key
The key is missing, mistyped or revoked. Paste the whole key (it starts with ua_) without “Bearer”, or create a new key in the console.
402insufficient_credit · key_budget_exceeded · plan_limit
No usage left. Choose a plan or add credit in Billing, create a key with a higher spending limit, or lower the max response length.
429rate_limit
More than 30 requests a minute or 3 at once. Turn off multiple swipes, auto-continue and parallel generations, then wait a minute.
503inference_unavailable
The model is not accepting requests right now, or the model ID does not match a live model. Check the model ID and the status page, then retry.
400 / 413unknown_model · invalid_request · context_limit
Wrong model ID, a response length above the output limit, or a context that is too long. Copy the model ID again and lower context or response size.

Ready to connect SillyTavern?

Create a key, paste the two values above, and send a message.

Get your key

Unrestricted AI is not affiliated with or endorsed by these apps; they accept any OpenAI-compatible endpoint. Our terms and the model provider’s terms still apply to role-play: you must be 18 or older and content must be lawful. Usage is billed per token from your plan allowance or credit, capped by each key’s spending limit.