> For the complete documentation index, see [llms.txt](https://docs.bitmind.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bitmind.ai/api-reference/api.md).

# API

Use the standard BitMind API for general integrations.

Base URL: `https://api.bitmind.ai`

This surface is intended for normal application and backend usage. Use it when you need standard detection access with regular API keys.

## Choosing an endpoint

Most integrations should start with [**Unified Detect**](/api-reference/api/v1-detect.md) (`POST /v1/detect`). It inspects your input, figures out whether it's an image, video, or text, and runs the right detector — so you don't have to branch on media type yourself.

Call a **type-specific endpoint** when you already know the media type and want to be explicit:

| Endpoint                                           | Use when                                                             |
| -------------------------------------------------- | -------------------------------------------------------------------- |
| [Unified Detect](/api-reference/api/v1-detect.md)  | You want one endpoint to auto-detect and route (recommended default) |
| [Detect Image](/api-reference/api/detect-image.md) | The input is always an image                                         |
| [Detect Video](/api-reference/api/detect-video.md) | The input is always a video (and you may want trim parameters)       |
| [Detect Text](/api-reference/api/detect-text.md)   | The input is always text                                             |

All of these return the same per-type result shapes; Unified Detect simply wraps the matching result in a `{ "mediaType", "result" }` envelope.