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

# Tool catalog

> The deterministic operations workflows and /v1/capabilities can invoke.

**31 tools.** These are not models. A tool does exactly one thing, deterministically,
for a fixed price: trim a video, extract text from a PDF, pack an archive, run a Python snippet.
No prompt, no sampling, no variance between two identical calls.

`GET /v1/tools` lists them at runtime — see [the API reference](/api-reference/tools).

They exist because most real work around a model is not inference. A pipeline that captions a
video needs the audio extracted before a speech model ever sees it, and paying inference prices
for `ffmpeg` would be absurd.

| Kind     | Tools | Page                              |
| -------- | ----- | --------------------------------- |
| Image    | 9     | [Image tools](/tools/image)       |
| Video    | 10    | [Video tools](/tools/video)       |
| Audio    | 4     | [Audio tools](/tools/audio)       |
| Document | 3     | [Document tools](/tools/document) |
| Archive  | 2     | [Archive tools](/tools/archive)   |
| Web      | 1     | [Web tools](/tools/web)           |
| Code     | 2     | [Code tools](/tools/code)         |

## Calling one

Every tool takes the same envelope — an `id`, and the `input` and `params` that tool declares:

```bash theme={null}
curl https://api.infery.ai/v1/capabilities/video.trim/run \
  -H "Authorization: Bearer $INFERY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"input": {"video_url": "https://example.com/in.mp4"}, "params": {"start": 0, "end": 15}}'
```

Each tool page lists that tool's parameters and gives runnable examples.