YOLO26

Use the YOLO26 model family through our Serverless Hosted API

We support YOLO26 inferencing via our Serverless Hosted API. YOLO26 is available in three task variants pretrained on COCO:

• Object detection

• Instance segmentation

• Keypoint (pose) detection

For self-hosted deployment, see Roboflow Inference.

Code samples

Install the SDK and the supervision library for annotation:

pip install inference-sdk supervision opencv-python

Pass your Roboflow API Key via the API_KEY environment variable. Each sample downloads a test image, runs inference through inference-sdk, decodes the response with supervision, and writes an annotated PNG to disk.

Object detection

import os
import urllib.request
import cv2
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)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
result = client.infer(image_path, model_id="yolo26n-640")
detections = sv.Detections.from_inference(result)

image = cv2.imread(image_path)
labels = [
    f"{cls} {conf:.2f}"
    for cls, conf in zip(detections.data["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("cars-highway-annotated.png", annotated)

Instance segmentation

import os
import urllib.request
import cv2
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)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
result = client.infer(image_path, model_id="yolo26n-seg-640")
detections = sv.Detections.from_inference(result)

image = cv2.imread(image_path)
labels = [
    f"{cls} {conf:.2f}"
    for cls, conf in zip(detections.data["class_name"], detections.confidence)
]
annotated = sv.MaskAnnotator().annotate(scene=image.copy(), detections=detections)
annotated = sv.BoxAnnotator().annotate(scene=annotated, detections=detections)
annotated = sv.LabelAnnotator().annotate(
    scene=annotated, detections=detections, labels=labels
)
cv2.imwrite("bicycle-annotated.png", annotated)

Keypoint detection

import os
import urllib.request
import cv2
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)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
result = client.infer(image_path, model_id="yolo26n-pose-640")
key_points = sv.KeyPoints.from_inference(result)

image = cv2.imread(image_path)
annotated = sv.VertexAnnotator(color=sv.Color.RED, radius=5).annotate(
    scene=image.copy(), key_points=key_points
)
cv2.imwrite("person-walking-annotated.png", annotated)

Default COCO aliases

Pass any of the following aliases as model_id when calling the SDK. The inference-sdk resolves each alias to its pretrained Roboflow Universe model client-side.

Task	Alias
Detection	yolo26n-640
Detection	yolo26s-640
Detection	yolo26m-640
Detection	yolo26l-640
Detection	yolo26x-640
Segmentation	yolo26n-seg-640
Segmentation	yolo26s-seg-640
Segmentation	yolo26m-seg-640
Segmentation	yolo26l-seg-640
Segmentation	yolo26x-seg-640
Pose	yolo26n-pose-640
Pose	yolo26s-pose-640
Pose	yolo26m-pose-640
Pose	yolo26l-pose-640
Pose	yolo26x-pose-640

The yolov26* prefix variants resolve to the same models.

Set api_url to match your deployment target:

• https://serverless.roboflow.com for the Serverless Hosted API.

• http://localhost:9001 for a local Inference server.

• Your Dedicated Deployment URL for a private endpoint.