> ## 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.

# Deepshi API

> Uncensored, OpenAI-compatible AI API for text, image, video, and music generation. One key, one balance, every model.

The Deepshi API is a single, OpenAI-compatible API for Deepshi's own models and the world's leading frontier models from OpenAI, Anthropic, Google, xAI, and others, all through the same key and balance.

<Tip>
  If you already use the OpenAI SDK, you can switch to Deepshi by changing two
  lines: the `base_url` and your API key. No other code changes are required.
</Tip>

## Why Deepshi

<CardGroup cols={2}>
  <Card title="Highly uncensored" icon="lock-open">
    Deepshi's own models are highly uncensored. They answer openly, with minimal filtering.
  </Card>

  <Card title="One API, every model" icon="layer-group">
    Deepshi and leading third-party models behind one base URL, one key, one billing balance.
  </Card>

  <Card title="OpenAI-compatible" icon="plug">
    Works with the official OpenAI SDKs and most tools that speak the OpenAI API. Point them at Deepshi and go.
  </Card>

  <Card title="Private by design" icon="shield-halved">
    Zero data retention. Your prompt and response content is never stored or used to train models. See [Privacy](/overview/privacy).
  </Card>
</CardGroup>

## Start here

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/get-started/quickstart">
    Make your first API call in under five minutes.
  </Card>

  <Card title="Authentication" icon="key" href="/get-started/authentication">
    Create an API key and authenticate your requests.
  </Card>

  <Card title="Models" icon="cubes" href="/models/overview">
    Browse the text, image, video, and music models you can call.
  </Card>

  <Card title="Credits & billing" icon="coins" href="/get-started/pricing-credits">
    Understand credits, pricing, and balance.
  </Card>
</CardGroup>

## What you can build

<CardGroup cols={3}>
  <Card title="Text & chat" icon="comments" href="/capabilities/text-and-chat">
    Chat and generation with streaming.
  </Card>

  <Card title="Image generation" icon="image" href="/capabilities/image-generation">
    Generate images from a text prompt.
  </Card>

  <Card title="Image editing" icon="pen" href="/capabilities/image-editing">
    Edit existing images with a prompt.
  </Card>

  <Card title="Video generation" icon="clapperboard" href="/capabilities/video-generation">
    Turn a prompt or an image into a video clip.
  </Card>

  <Card title="Music generation" icon="music" href="/capabilities/audio-generation">
    Generate full songs from a style prompt, with optional lyrics.
  </Card>

  <Card title="Tool calling" icon="wrench" href="/capabilities/tool-calling">
    Let models call your functions and external tools.
  </Card>

  <Card title="Reasoning" icon="brain" href="/capabilities/reasoning">
    Models that think step by step on hard problems.
  </Card>

  <Card title="Structured outputs" icon="code" href="/capabilities/structured-outputs">
    Force responses that match a JSON schema.
  </Card>
</CardGroup>