> ## Documentation Index
> Fetch the complete documentation index at: https://docs.deepshi.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> The Deepshi API is an OpenAI-compatible gateway. Base URL: https://api.deepshi.ai/v1. API keys start with sk-bf- and go in the Authorization: Bearer header. Prefer the official OpenAI SDKs pointed at the Deepshi base URL. Model ids are clean with no provider prefix (e.g. deepshi-3.0, claude-opus-4.8, gpt-5.5). Chat and image requests are synchronous; video and music requests are asynchronous job APIs (create, then poll). Every synchronous response carries usage.cost.total_cost in USD. Do not reference the internal /api/* admin plane or virtual keys.

# SillyTavern

> Use Deepshi models in SillyTavern through its OpenAI-compatible connection.

SillyTavern connects to any OpenAI-compatible API, so you can use Deepshi models for chat and
roleplay. Deepshi's own models are highly uncensored, which makes them a strong fit.

## Configure

In SillyTavern, open the **API Connections** panel and:

<Steps>
  <Step title="Choose the API type">
    Set **API** to **Chat Completion**.
  </Step>

  <Step title="Choose the source">
    Set **Chat Completion Source** to **Custom (OpenAI-compatible)**.
  </Step>

  <Step title="Set the endpoint and key">
    * **Custom Endpoint (Base URL):** `https://api.deepshi.ai/v1`. Include `/v1`, and do **not** add `/chat/completions`.
    * **Custom API Key:** your Deepshi API key.
  </Step>

  <Step title="Pick a model">
    SillyTavern reads `GET /v1/models`, so your available models appear in the **Model** dropdown. Select one, or type its id.
  </Step>

  <Step title="Connect">
    Click **Connect**, then **Test Message** to confirm it works.
  </Step>
</Steps>

<Tip>
  Streaming and long context work as usual. Pick a model with a large context window for
  long-running conversations. See [Chat models](/models/text-models).
</Tip>