Locate every object your agent can name in a photo

Superlinked gives your agent one API to name the objects it cares about and get a pixel box and score for each one it finds.

Get started

labels ["sale sign"]

sale sign 0.35 sale sign 0.32 sale sign 0.29 sale sign 0.26 sale sign 0.32 sale sign 0.27 sale sign 0.37 sale sign 0.26 sale sign 0.26 sale sign 0.27

10 sale signs located in one call; the 4 it missed stay dashed

55 of 57 returned boxes sit on the object your agent asked for

View evidence

Almost every box it draws is one your agent can act on: 55 of the 57 boxes Grounding DINO returned sit on the object it was asked for, across all 9 recorded photos. Dashed outlines mark each miss on the hero and the cards below.

shipping container 0.44 forklift 0.39 person 0.41 forklift 0.35 · duplicate person 0.25 shipping container 0.25 · duplicate

Container loading dock in Thailand

forklift 1 of 1 found
shipping container 1 of 1 found
person 2 of 2 found

2 more boxes on objects already found

Goterrestrial on Wikimedia Commons · CC BY 4.0

safety vest 0.33 safety vest 0.33 safety vest 0.30 safety vest 0.31 safety vest 0.34 safety vest 0.27 safety vest 0.31 safety vest 0.29 safety vest 0.26

Food box packing floor

safety vest 9 of 14 found

U.S. Department of Agriculture · public domain

person 0.50 person 0.52 person 0.48 person 0.46 person 0.45 person 0.40 person 0.37 person 0.39 shopping cart 0.37 yellow price sign 0.36 shopping cart 0.29 person 0.33 · duplicate

Supermarket produce department

person 8 of 8 found
shopping cart 2 of 2 found
yellow price sign 1 of 7 found

1 more box on objects already found

Dean Hochman on Flickr · CC BY 2.0

7 up bottle 0.27 7 up bottle 0.29 price tag 0.25 · wrong object

Soft drink shelf

price tag 0 of 11 found
7 Up bottle 2 of 3 found

one box labelled price tag spans the whole photo

SMC on Wikimedia Commons · public domain

forklift 0.57 pallet jack 0.27 · wrong object

Distribution center in San Juan, Puerto Rico

forklift 1 of 1 found
pallet jack 0 of 1 found

one box labelled pallet jack sits on another object

FEMA · public domain

person 0.75 person 0.72 person 0.67 pallet jack 0.32

Staging hall at the Javits Center, New York

pallet jack 1 of 3 found
person 3 of 3 found

The National Guard on Flickr · CC BY 2.0

8 of the 9 recorded photos appear on this page. Those 55 boxes cover 52 of the 88 objects counted by hand; Grounding DINO also drew 3 extra boxes on objects it had already found and put 2 on the wrong object.

Send the labels and get back pixel boxes to crop or flag

View on GitHub

from pathlib import Path
from sie_sdk import SIEClient
client = SIEClient(
    api_key="API keysk-sie-…",
    base_url="https://api.superlinked.com",
)
image = {"data": Path(imagehangar-pallet-jacks.jpgbrowse).read_bytes(), "format": "jpeg"}
result = client.extract(
    "modelIDEA-Research/grounding-dino-base",
    {"images": [image]},
    labels=[
        "querypallet jack",
    ],
)
for obj in result["objects"]:
    print(obj["label"], obj["score"], obj["bbox"])

import { readFile } from 'node:fs/promises';
import { SIEClient } from '@superlinked/sie-sdk';

const client = new SIEClient('https://api.superlinked.com', {
  apiKey: 'sk-sie-…',
});

const image = await readFile("hangar-pallet-jacks.jpg");
const result = await client.extract(
  'IDEA-Research/grounding-dino-base',
  { images: [image] },
  { labels: ["pallet jack"] },
);
console.log(result.objects);

images_bytes=$(base64 < 'hangar-pallet-jacks.jpg' | tr -d '\n')
curl https://api.superlinked.com/v1/extract/IDEA-Research%2Fgrounding-dino-base \
  -H "Authorization: Bearer sk-sie-…" \
  -H "Content-Type: application/json" \
  -d "{\"items\":[{\"images\":[{\"data\":\"$images_bytes\",\"format\":\"jpeg\"}]}],\"params\":{\"labels\":[\"pallet jack\"]}}"

Build the "Detect" capability into my app using the Superlinked Inference Engine (SIE).

Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: IDEA-Research/grounding-dino-base (SIE primitive: /extract). Keep the model id configurable.

Task
- Input: an uploaded image plus the object labels to find.
- Behaviour: return the named objects with confidence scores and bounding boxes
- Call the selected SIE primitive once per request and map the response into your domain type.

Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.

Run

Output

pallet jack0.44[349, 92, 392, 195]

pallet jack0.37[429, 390, 199, 307]

pallet jack0.30[87, 526, 233, 386]

pallet jack0.27[843, 287, 267, 281]

4 objects with bounding boxes

PRICE

$ / 1k images $ / 1M input tokens $ / 1M output tokens ↓

$0.232 SIE OWLv2 Base

$0.309 SIE Grounding DINO

AWS Rekognition $1

Google Vision Labels $1.5

Google Vision Objects $2.25

OpenAI GPT-5.4 mini $0.75

OpenAI GPT-5.4 mini $4.5

QUALITY

AP · COCO ↑

SIE Grounding DINO 0.58

0.56

0.55

SIE OWLv2 Base 0.43

0.42

0.41

LATENCY

p50 ms ↓

SIE Grounding DINO 786ms

900ms

950ms

SIE OWLv2 Base 1008ms

1120ms

1180ms

Deploy your way

Managed Cloud

Full compute toolkit for your agents with zero ops.

No idle GPUs, pay for what you use
Fits your stack: SDK, API, CLI, MCP
Zero lock-in, self-host the same stack
SOC 2 Type 2, US or EU data residency

$50 Example credit balance

1.3B tokens embedded

120k pages parsed

27M tokens generated (1:1 in:out)

Get started

no credit card required

Self-host with K8s

Easy & scalable deployment in your own cloud.

Terraform to your cloud in minutes
Apache-2.0, same engine as Cloud
Scales to zero, no bill between jobs
Per-tenant pools, no noisy neighbors

Agent prompt

Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deploymentDeploy SIE to our GCP project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deploymentDeploy SIE to our Azure AKS cluster via helm install. Requirements: superlinked.com/docs/deployment

Deploy guide

Run locally

Run the same models on your own machine.

Runs on NVIDIA GPU or Apple Silicon
One command, no Docker or cluster
All 100+ Cloud models, fully offline
Same SDK and IDs, no code changes

pip install "sie-server[local]" && sie-server servepip install "sie-server[local]" && sie-server serve --device cuda

Quickstart