Skip to main content
SillyTavern is the power-user / roleplay front-end for local models, with fine-grained control over prompts, sampling, and characters. Its Chat Completion backend can point at any custom OpenAI-compatible endpoint — set the source to Custom (OpenAI-compatible), enter https://api.tokios.com/v1 and your sk-tok-… key, and SillyTavern drives a model running on your own hardware.

​
Prerequisites

Connector paired

Install and pair tokios-connector next to the model you want SillyTavern to reach.

Model registered

Register a deployment (public name) for that model.

API key created

Create an sk-tok-… key, optionally scoped to that deployment.

Supported backends

Confirm your local backend (Ollama, llama.cpp, vLLM, LM Studio) is running.

​
Connect SillyTavern to Tokios

1

Open API Connections

Click the plug icon to open the API Connections panel.
2

Choose Chat Completion → Custom (OpenAI-compatible)

Set API to Chat Completion, then set Chat Completion Source to Custom (OpenAI-compatible).
3

Set the endpoint and key

Fill in the custom-endpoint fields:
Use https://api.tokios.com/v1. SillyTavern adds /chat/completions itself, so do not append it. If a connection fails and you left /v1 off, adding it is the first thing to try.
4

Enter your deployment as the model and connect

Enter the public deployment name you registered in the Models tab — for example, gemma-tunnel — as the model id, then click Connect. This is the value SillyTavern sends in the model field, not your backend’s local model id.
Replace gemma-tunnel with the deployment name you registered, and sk-tok-YOUR_KEY with your own key. Never commit either into a shared config file.

​
Power-user front-end, model on your hardware

SillyTavern gives you deep control over prompting and sampling; Tokios gives whatever model you’re running a stable, authenticated endpoint. The connector next to your model dials out to Tokios, and SillyTavern — on the same machine or another one — calls https://api.tokios.com/v1 with your sk-tok-… key. Your prompts and characters stay yours; only the connector’s outbound tunnel touches Tokios.

​
Troubleshooting

The API key SillyTavern sent is missing, malformed, or has been revoked. Confirm you pasted the full sk-tok-… key with no extra whitespace, and check its status on the Keys tab.
The model value doesn’t match a registered deployment, or the base URL is wrong. Confirm the model name matches the public name on the Models tab, that the base URL is https://api.tokios.com/v1, and that you did not append /chat/completions.
The connector for that deployment is offline or at its concurrency cap. Check the Connectors tab — the connector needs to show as Online, and the machine running it needs to still be up and reachable.

​
Next steps

Compatible clients

See base URL and key setup for other OpenAI- and Anthropic-compatible clients.

API keys

Create, scope, and rotate sk-tok-… keys for teammates and agents.