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

# Quickstart

This page walks through the shortest path from a fresh Python environment to a working inference call against a public Roboflow Universe model. Once you have this working you can swap in your own workspace and project.

## 1. Install

You need `Python >=3.10`.

```bash
pip install roboflow
```

If you only need lightweight CLI / Vision Events functionality without OpenCV / NumPy / Pillow, install the lite variant instead:

```bash
pip install roboflow-slim
```

## 2. Authenticate

Grab your API key from <https://app.roboflow.com/settings/api>, then set it as an environment variable:

```bash
export ROBOFLOW_API_KEY=rf_xxxxx
```

Verify:

```bash
roboflow auth status
```

The CLI prints your active workspace and a masked API key.

## 3. Run inference

The fastest way to see a result is the CLI against a public Universe model:

```bash
roboflow infer ~/Downloads/my-image.jpg -m poker-cards-cxcvz/1 -c 0.5
```

Or with the Python SDK:

```python
import roboflow

rf = roboflow.Roboflow()  # picks up ROBOFLOW_API_KEY
project = rf.workspace("roboflow-100").project("poker-cards-cxcvz")
model = project.version(1).model

predictions = model.predict("my-image.jpg", confidence=50, overlap=30).json()
print(predictions)
```

Or with curl against the REST API:

```bash
curl -F "file=@my-image.jpg" \
  "https://serverless.roboflow.com/infer/workflows/roboflow-100/poker-cards-cxcvz/1?api_key=$ROBOFLOW_API_KEY"
```

## 4. Pick a tool to go deeper

The three developer tools serve different needs - see [Choosing the Right Tool](/developer/choosing-the-right-tool.md) for guidance on when to use each.

* **CLI** - best for scripts, ad-hoc operations, and AI coding agents. See [Using the CLI](/developer/command-line-interface/using-the-cli.md).
* **Python SDK** - best for scheduled jobs, notebooks, and integrations inside Python applications. See [Using the Python SDK](/developer/python-sdk/using-the-python-sdk.md).
* **REST API** - best for non-Python applications and webhooks. See [Using the REST API](/developer/rest-api/using-the-rest-api.md).

## 5. Try a workflow recipe

The [Recipes](/developer/recipes/recipes.md) section has end-to-end task walkthroughs that combine the CLI, SDK, and REST API:

* [Upload, Train, and Deploy a Model](/developer/recipes/upload-train-and-deploy.md)
* [Process a Video Stream](/developer/recipes/process-a-video-stream.md)
* [Watch a Folder for New Images](/developer/recipes/watch-a-folder.md)