> 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/deploy/supported-models/roboflow-3.md).

# Roboflow 3.0

Roboflow 3.0 is Roboflow's in-house model architecture. It supports object detection, instance segmentation, classification, and keypoint detection. You train Roboflow 3.0 models on the Roboflow platform and deploy them through our [Serverless Hosted API](/deploy/serverless-hosted-api-v2.md).

For self-hosted deployment, see [Roboflow Inference](https://inference.roboflow.com/).

{% hint style="info" %}
Roboflow 3.0 has no public default COCO aliases. You call your own trained model using its `project/version` identifier from your [Roboflow Project](https://app.roboflow.com/).
{% endhint %}

## Code samples

Install the [Inference SDK](https://inference.roboflow.com/) and [supervision](https://supervision.roboflow.com/):

```bash
pip install inference-sdk supervision
```

The samples below run inference against a Roboflow 3.0 model you have trained. Replace `your-project/1` with your model URL and version. Pass your [Roboflow API Key](https://app.roboflow.com/settings/api) via the `API_KEY` environment variable.

### Object detection

```python
import os
import cv2
import urllib.request
import supervision as sv
from inference_sdk import InferenceHTTPClient

image_url = "https://storage.googleapis.com/com-roboflow-marketing/notebooks/examples/cars-highway.png"
image_path = "cars-highway.png"
urllib.request.urlretrieve(image_url, image_path)

image = cv2.imread(image_path)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
result = client.infer(image, model_id="your-project/1")

detections = sv.Detections.from_inference(result)
labels = [
    f"{class_name} {confidence:.2f}"
    for class_name, confidence
    in zip(detections.data.get("class_name", []), detections.confidence)
]

annotated = sv.BoxAnnotator().annotate(scene=image.copy(), detections=detections)
annotated = sv.LabelAnnotator().annotate(scene=annotated, detections=detections, labels=labels)
cv2.imwrite("output.png", annotated)
```

### Instance segmentation

```python
import os
import cv2
import urllib.request
import supervision as sv
from inference_sdk import InferenceHTTPClient

image_url = "https://storage.googleapis.com/com-roboflow-marketing/notebooks/examples/bicycle.png"
image_path = "bicycle.png"
urllib.request.urlretrieve(image_url, image_path)

image = cv2.imread(image_path)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
result = client.infer(image, model_id="your-project/1")

detections = sv.Detections.from_inference(result)
labels = [
    f"{class_name} {confidence:.2f}"
    for class_name, confidence
    in zip(detections.data.get("class_name", []), detections.confidence)
]

annotated = sv.MaskAnnotator().annotate(scene=image.copy(), detections=detections)
annotated = sv.LabelAnnotator().annotate(scene=annotated, detections=detections, labels=labels)
cv2.imwrite("output.png", annotated)
```

### Keypoint detection

```python
import os
import cv2
import urllib.request
import supervision as sv
from inference_sdk import InferenceHTTPClient

image_url = "https://storage.googleapis.com/com-roboflow-marketing/notebooks/examples/person-walking.png"
image_path = "person-walking.png"
urllib.request.urlretrieve(image_url, image_path)

image = cv2.imread(image_path)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
result = client.infer(image, model_id="your-project/1")

key_points = sv.KeyPoints.from_inference(result)

annotated = sv.EdgeAnnotator(color=sv.Color.BLUE, thickness=2).annotate(
    scene=image.copy(), key_points=key_points
)
annotated = sv.VertexAnnotator(color=sv.Color.GREEN, radius=5).annotate(
    scene=annotated, key_points=key_points
)
cv2.imwrite("output.png", annotated)
```

### Classification

Classification responses contain a list of class predictions with confidences, so visualization is not applicable. Read the top class directly from the response.

```python
import os
import cv2
import urllib.request
from inference_sdk import InferenceHTTPClient

image_url = "https://storage.googleapis.com/com-roboflow-marketing/notebooks/examples/cars-highway.png"
image_path = "cars-highway.png"
urllib.request.urlretrieve(image_url, image_path)

image = cv2.imread(image_path)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
result = client.infer(image, model_id="your-project/1")

print(f"Top class: {result['top']} ({result['confidence']:.4f})")
```

{% hint style="info" %}
Set `api_url` to match your deployment target:

* `https://serverless.roboflow.com` for the Serverless Hosted API.
* `http://localhost:9001` for a local [Inference](https://inference.roboflow.com/) server.
* Your [Dedicated Deployment](/deploy/dedicated-deployments.md) URL for a private endpoint.
  {% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.roboflow.com/deploy/supported-models/roboflow-3.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.