# 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)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.roboflow.com/developer/quickstart.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.