Apps are tools that do one thing well.
What's an app?
An app takes input, does something, and returns output.
Examples:
stable-diffusion— prompt in, image outwhisper— audio in, text outsummarize— long text in, short text out
Inputs and outputs
Every app has a schema:
code
1stable-diffusion2├── Input3│ ├── prompt (text, required)4│ ├── style (text, optional)5│ └── size (choice, optional)6└── Output7 └── image (file)The schema tells you what to provide and what you'll get back.
Where apps come from
| Source | Description |
|---|---|
| The Grid | 100+ pre-built apps from inference.sh |
| Community | Public apps from other users |
| You | Apps you create and deploy |
How to use apps
- Directly — Run from the workspace UI
- In Flows — Chain with other apps
- As Agent Tools — Let agents call them
- Via API — Run programmatically
Creating Apps
You can create your own apps using Python. An app consists of:
inference.py— The codeinf.yml— Configuration
Code Structure
python
1class AppSetup(BaseAppInput):2 """Static configuration (restart required)"""3 model_name: str4 5class AppInput(BaseAppInput):6 """Request arguments (per run)"""7 prompt: str8 9class App(BaseApp):10 async def setup(self, config: AppSetup):11 pass12 13 async def run(self, input: AppInput):14 # Process request15 passNext
→ Tasks