SillyTavern with an uncensored API: setup in 2 minutes

SillyTavern is great, but the model behind it decides how good your chats are. Local models need a strong GPU, and the big hosted APIs refuse or water down anything dark, violent or adult. Orrevan sits in between: hosted uncensored and abliterated models behind an OpenAI-compatible API, so SillyTavern connects to it like to any other provider.

What you need

• SillyTavern (any recent version)
• An Orrevan account with a little credit (top-ups start at $2)
• An API key from Developers

Setup

1. Open API Connections (the plug icon).
2. Set API to Chat Completion.
3. Set Chat Completion Source to Custom (OpenAI-compatible).
4. Custom Endpoint (Base URL): https://orrevan.com/api/v1
5. Custom API Key: your key, it starts with orv_.
6. Click Connect. Pick a model from Available Models, or type it into Enter a Model ID, for example orrevan/deepseek-v4.1-flash-unc.

That is it. Send a message to test it.

Which model?

Models behave differently, so try two or three with your own characters. Good starting points:

Model ID	Why
orrevan/deepseek-v4.1-flash-unc	Cheap, fast, 1M token context for long chats
orrevan/abliterated-model-large-v2	Our strongest model, best for complex stories
orrevan/qwen38-obl	Very cheap all-rounder
orrevan/mimo-v26-flash-abl	Also understands images

The full list with prices is on the homepage and at https://orrevan.com/api/v1/models. Not every model is equally unfiltered: if one refuses, switch to an abliterated one.

What does it cost?

You pay per token, no subscription. A typical roleplay turn with about 4,000 tokens of context and a 300 token reply costs around $0.003 on DeepSeek V4.1 Flash Uncensored. So $2 lasts for several hundred messages. Longer context means higher cost per message, because the whole chat history is sent each time.

Tips

• Reasoning: SillyTavern sends its Reasoning Effort setting. Models that support it think longer on higher levels; the others simply ignore it.
• Context size: keep the context limit in SillyTavern sensible (for example 16k to 32k). It saves money and most stories do not need more.
• Key limits: in Developers you can give the key a daily spending limit, so a leaked key cannot drain your balance.

Privacy

Your chats stay in SillyTavern on your own machine. Orrevan does not store the content of API requests as chats and does not train on your data. For billing we only record token counts. To answer, your input is sent to the provider of the selected model, details are in the privacy policy.

Create an account and get your key.