> ## 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.

# LibreChat

> Use Deepshi models in LibreChat through its OpenAI-compatible custom endpoint.

[LibreChat](https://www.librechat.ai/) is a self-hosted, open-source chat UI. Because the Deepshi chat API is OpenAI-compatible, you can add Deepshi as a custom endpoint and use its models for chat and roleplay.

## Add Deepshi as an endpoint

Add Deepshi under `endpoints.custom` in `librechat.yaml`:

```yaml theme={null}
endpoints:
  custom:
    - name: "Deepshi"
      apiKey: "${DEEPSHI_API_KEY}"
      baseURL: "https://api.deepshi.ai/v1"
      models:
        default: ["deepshi-3.0", "deepshi-2.0"]
        fetch: true
```

`fetch: true` pulls the full model list from `GET /v1/models`. Set `DEEPSHI_API_KEY` in your `.env`, then restart LibreChat and pick Deepshi from the endpoint menu.

<Tip>
  Deepshi's own models are highly uncensored, which makes them a strong fit for
  open-ended chat and roleplay. Browse ids on the [text models](/models/text-models) page.
</Tip>