Find objects more accurately than GPT‑6.1 Sol, 982x faster

Meta's SAM 3 finds the objects you name and returns their boxes. SIE is the open-source inference engine that serves it through one API.

Get started Run in your cloud

SIE SAM 3

16 of 17 vehicles boxed

Asked for car, bus, truck

GPT‑6 Luna and Claude Sonnet 5.5 miss vehicles in crowded photos

GPT‑6 Luna (high reasoning)

6 of 15 vehicles boxed

Asked for car, bus, truck

A drone photo of a motorway interchange with slip roads: a part of it with 15 vehicles, and the 14 boxes GPT-6 Luna (high reasoning) returned there. — 14 boxes in this view; 6 cover a vehicle by half or more, the other 8 sit partly off a vehicle. Whole photo: 16 of 41 vehicles, in 63.5 s.

Claude Sonnet 5.5 (adaptive thinking)

0 of 11 vehicles boxed

Asked for car, bus, truck

A drone photo of a road junction with queues of cars: a part of it with 11 vehicles, and the 24 boxes Claude Sonnet 5.5 (adaptive thinking) returned there. — 24 boxes in this view, none touching a vehicle. Whole photo: 0 of 42 vehicles, in 6.8 s.

NBC 5 Dallas-Fort Worth Dallas AI cameras missed a license plate they were meant to blur; the city covered it by hand
The city "had to add that black box to redact the plate number because it was still visible in the original image."
23 September 2026
arXiv:2607.06420 In crowded scenes, GPT-5.5 counted exactly right 1 time in 5 and Claude Opus 4.8 1 time in 100
HoloCount: A Holistic Visual Counting Benchmark for MLLMs

Deng, Qiao and Wan

“These results confirm that dense scenes cause systematic under-counting”
7 July 2026

Find objects more accurately than GPT‑6.1 Sol, 982x faster

Run this eval

Objects boxed correctly

F1, mean of four sets ↑

SIE SAM 3

SIE SAM 3 0.62

GPT-6.1 Sol

GPT-6.1 Sol 0.60

Claude Sonnet 5.5

0.39 Claude Sonnet 5.5

GPT‑6 Luna (high reasoning)

0.36 GPT‑6 Luna (high reasoning)

GPT‑6 Luna (medium reasoning)

0.36 GPT‑6 Luna (medium reasoning)

Claude Haiku 5.5

0.31 Claude Haiku 5.5

Time per photo

median ↓

SIE SAM 3

82.2 ms SIE SAM 3

Claude Haiku 5.5

4.15 s Claude Haiku 5.5

Claude Sonnet 5.5

5.62 s Claude Sonnet 5.5

GPT‑6 Luna (medium reasoning)

22.90 s GPT‑6 Luna (medium reasoning)

GPT‑6 Luna (high reasoning)

35.30 s GPT‑6 Luna (high reasoning)

GPT-6.1 Sol

GPT-6.1 Sol 80.74 s

Cost per 1,000 photos

USD ↓

SIE SAM 3

$0.25 SIE SAM 3

Claude Haiku 5.5

$0.76 Claude Haiku 5.5

GPT‑6 Luna (medium reasoning)

$1.71 GPT‑6 Luna (medium reasoning)

GPT‑6 Luna (high reasoning)

$2.95 GPT‑6 Luna (high reasoning)

Claude Sonnet 5.5

$13.27 Claude Sonnet 5.5

GPT-6.1 Sol

GPT-6.1 Sol $59.98

Tested: 300 crowded photos; 17,222 objects across four public benchmarks
Scored: Correct label and at least 50% box overlap; macro-average F1
Prices: SIE Serverless; provider list prices on recorded usage
Timing: SIE timed on a GPU server with the client alongside; providers over their public APIs

Send a photo and the names to count, get a box for each one

from urllib.request import urlopen
from sie_sdk import SIEClient
client = SIEClient(api_key="API keysk-sie-…")
image_bytes = urlopen(imagejunction.jpgbrowse).read()
image = {"data": image_bytes, "format": "jpeg"}
result = client.extract(
    "modelfacebook/sam3",
    {"images": [image]},
    labels=[
        "labelcar",
        "labelbus",
        "labeltruck",
    ],
)
for obj in result["objects"]:
    print(obj["label"], obj["score"], obj["bbox"])

import { SIEClient } from '@superlinked/sie-sdk';

const client = new SIEClient(undefined, { apiKey: 'sk-sie-…' });

const source = await fetch("https://huggingface.co/datasets/superlinked/sie-task-evidence/resolve/0031c63f8da106f93dc6537d38f03139b7a0bb44/detect-api-input/2026-10-14/junction.jpg");
if (!source.ok) throw new Error('Could not load the original photo.');
const image = new Uint8Array(await source.arrayBuffer());
const result = await client.extract(
  'facebook/sam3',
  { images: [image] },
  { labels: ["car","bus","truck"] },
);
console.log(result.objects);

curl --fail --silent --show-error --location --output 'junction.jpg' 'https://huggingface.co/datasets/superlinked/sie-task-evidence/resolve/0031c63f8da106f93dc6537d38f03139b7a0bb44/detect-api-input/2026-10-14/junction.jpg' || exit 1
images_bytes=$(base64 < 'junction.jpg' | tr -d '\n')
curl https://api.superlinked.com/v1/extract/facebook%2Fsam3 \
  -H "Authorization: Bearer sk-sie-…" \
  -H "Content-Type: application/json" \
  -d "{\"items\":[{\"images\":[{\"data\":\"$images_bytes\",\"format\":\"jpeg\"}]}],\"params\":{\"labels\":[\"car\",\"bus\",\"truck\"]}}"

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: facebook/sam3 (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

51 objects returned for car, bus, truck

A drone photo of a road junction with queues of cars, with the 51 boxes SAM 3 returned for car, bus, truck.

label	score	bbox [x, y, w, h]
car	0.885	[3267, 363, 49, 46]
car	0.877	[3354, 459, 45, 50]
car	0.875	[3544, 1203, 49, 42]
car	0.872	[2370, 446, 51, 56]
car	0.860	[2722, 1377, 56, 31]
car	0.857	[282, 787, 60, 29]

and 45 more, highest score first. Score is SAM 3's own match score, not a probability.

Start finding objects in your photos

Serverless API

We host the models; you call one API.

No idle GPUs, pay for what you use
Fits your stack: SDK, API, CLI, MCP
Self-host the same open-source engine
SOC 2 Type 2, US or EU data residency
Create an account to try Serverless

Get started

Self-hosted (Kubernetes)

Your data stays in your cloud, backed by our engineers.

Terraform modules for your cloud
Apache-2.0, same engine as Serverless
GPU workers scale to zero between jobs
Separate worker pools for each tenant

Agent prompt Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deployment.

Deploy SIE to our Google Cloud project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deployment.

Deploy SIE to our Azure subscription with the superlinked/sie/azure Terraform module. Docs: superlinked.com/docs/deployment.

Deploy SIE to our Alibaba Cloud account with the superlinked/sie/alicloud Terraform module. Docs: superlinked.com/docs/deployment.

Talk to us Deploy guide

Run locally

The open-source server on your own machine.

NVIDIA GPU
One container, no cluster
Process your data fully offline
Same SDK and model IDs as Serverless

docker run --gpus all -p 8080:8080 -e HF_TOKEN ghcr.io/superlinked/sie-server:latest-cuda12-transformers5

Quickstart

Switch to SIE in 5 minutes

from openai import OpenAI

client = OpenAI()
resp = client.chat.completions.create(
    model="gpt-6-luna",
    messages=messages,
    response_format=schema,
)
objects = json.loads(resp.choices[0].message.content)["objects"]

from google import genai

client = genai.Client()
resp = client.models.generate_content(
    model="gemini-3.8-flash",
    contents=[image, prompt],
    config=config,
)
objects = json.loads(resp.text)

import boto3

client = boto3.client("rekognition")
resp = client.detect_labels(Image={"Bytes": image_bytes})
# Rekognition's own label list; boxes only for the labels it knows
objects = [
    (label["Name"], box["BoundingBox"])
    for label in resp["Labels"]
    for box in label.get("Instances", [])
]

SIE

from sie_sdk import SIEClient

client = SIEClient(api_key="YOUR_SIE_API_KEY")
result = client.extract(
    "facebook/sam3",
    {"images": [image_bytes]},
    labels=["car", "bus", "truck"],
)
objects = result["objects"]

from sie_sdk import SIEClient

client = SIEClient(api_key="YOUR_SIE_API_KEY")
result = client.extract(
    "facebook/sam3",
    {"images": [image_bytes]},
    labels=["car", "bus", "truck"],
)
objects = result["objects"]

from sie_sdk import SIEClient

client = SIEClient(api_key="YOUR_SIE_API_KEY")
result = client.extract(
    "facebook/sam3",
    {"images": [image_bytes]},
    labels=["car", "bus", "truck"],
)
objects = result["objects"]