SillyTavern with 6bee.ai

SillyTavern connects to 6bee.ai as a Custom (OpenAI-compatible) source. The models are uncensored, so role-play does not need a jailbreak prompt.

Before you start

SillyTavern installed and running.
Create an account with a verified email address, add prepaid balance, then create a key on the console's API keys page. Keep the key secret.
Model IDs are listed in the console and returned by GET https://api.6bee.ai/v1/models. Replace <model id> with one of them.

Connect

Open API Connections (the plug icon) and set:

API: Chat Completion
Chat Completion Source: Custom (OpenAI-compatible)
Custom Endpoint (Base URL): https://api.6bee.ai/v1
Custom API Key: <your key>
Model: Pick one under Available Models, or type a model ID.

Click Connect. The status turns green when the key and the endpoint are right.

Context and response length

In the sampler settings (the sliders icon), set the context size and the response length to fit the model you chose. Long chats with lorebooks grow quickly:

Context: Input plus output up to the model’s window: 128K to 1M tokens, depending on the model.
Output: max_tokens up to the model’s output cap: 16,384 to 131,072, depending on the model. Larger values are lowered to the cap, not rejected. If omitted: 8,192 to 32,768.

SillyTavern trims old messages once the context size you set is reached, so a correct value prevents 400 errors.

What uncensored means for role-play

The models are tuned to stop refusing, so mature themes, violence and morally grey characters work without prompt tricks. The Acceptable Use rules still apply whatever a model will write. In particular, sexual content involving minors is prohibited in any form, including fiction.

Chats are not stored on 6bee.ai. SillyTavern keeps its own copy on your machine. See what is and is not stored.

Troubleshooting

HTTP 401: The key is missing or wrong. Copy it again from the console, without spaces or quotes.
Model not found: The model ID does not match. List the valid IDs with GET /v1/models or check the console.
HTTP 429: You are over a per-account limit (requests, input tokens or concurrency). The Retry-After header says how long to wait.
HTTP 400 on long sessions: The request no longer fits the model’s context window. Compact or clear the conversation, or switch to a model with a larger window.
Request rejected for balance: Each request first reserves its input plus max_tokens of output. Top up, or lower max_tokens.
Connect fails with 404: The endpoint must be https://api.6bee.ai/v1. Do not add /chat/completions.