Back to models

Model

Nobility 5

Our general-purpose vision model for detecting and drawing bounding boxes around any object-looking thing in an image, from small to large. Built to be the default choice for everyday detection work, across any object category you point it at.

At a glance.

The core specs that define what Nobility 5 is built for.

Object coverage

Any object

Not limited to a fixed label set — detects any object-looking region, named or unnamed.

Output

Bounding boxes

Returns coordinates for every detected object in a single image request.

Best for

Everyday detection

Balanced speed and recall for scenes with a mix of small and large objects.

Why teams pick Nobility 5.

A few reasons this is the default model for most workloads.

01

Open-vocabulary detection

Not restricted to a fixed category list — it boxes anything that looks like an object, named or not.

02

Small to large

Finds tiny objects in high-resolution scenes as reliably as it finds large, obvious ones.

03

Consistent behaviour

Behaves the same way in production as it does in testing, so what you evaluate is what you deploy.

04

Simple upgrade path

Same request format as Nobility 5 Mini and Nobility 5 Pro, so switching tiers doesn't mean rewriting your integration.

A simple API.

A single endpoint for object detection and bounding boxes. Drop it into whatever stack you already run.

# one request, any language curl https://api.noble.ai/v1/detect \ -H "Authorization: Bearer $KEY" \ -d '{ "model": "nobility-5", "image": "https://example.com/photo.jpg", "prompt": "detect all objects" }'

Ready to build with Nobility 5?

Start building today, or talk to our team about what you need.