Most AI tasks no longer need a frontier model Read launch post

marqo fashionSigLIP

An open image and text embedding model, for finding photos with words. Marqo/marqo-fashionSigLIP

  • Accuracy

    0.838

    Flickr30k image to text, nDCG@10

  • Time per request

    Not timed one request at a time

  • Serverless price

Call it

from sie_sdk import SIEClient
​
client = SIEClient("http://localhost:8080")
​
query = "querya red leather handbag"
images = [
imageblack-camera.pngbrowse,
imageblue-running-sneaker.pngbrowse,
imagegreen-backpack.pngbrowse,
imagered-leather-handbag.pngbrowse,
]
​
# Encode the text query + each catalog image in one batch.
items = [{"text": query}] + [{"images": [f]} for f in images]
vecs = client.encode("modelMarqo/marqo-fashionSigLIP", items)
print(vecs)
import { readFile } from 'node:fs/promises';
import { SIEClient } from '@superlinked/sie-sdk';

const client = new SIEClient('http://localhost:8080');

const query = "a red leather handbag";
const imagePaths = [
  "black-camera.png",
  "blue-running-sneaker.png",
  "green-backpack.png",
  "red-leather-handbag.png",
];
const images = await Promise.all(imagePaths.map((path) => readFile(path)));

// Encode the text query + each catalog image in one batch.
const items = [{ text: query }, ...images.map((image) => ({ images: [image] }))];
const vecs = await client.encode('Marqo/marqo-fashionSigLIP', items);
console.log(vecs);
image_0=$(base64 < 'black-camera.png' | tr -d '\n')
image_1=$(base64 < 'blue-running-sneaker.png' | tr -d '\n')
image_2=$(base64 < 'green-backpack.png' | tr -d '\n')
image_3=$(base64 < 'red-leather-handbag.png' | tr -d '\n')
curl http://localhost:8080/v1/encode/Marqo%2Fmarqo-fashionSigLIP \
  -H "Content-Type: application/json" \
  -d "{\"items\":[{\"text\":\"a red leather handbag\"},{\"images\":[{\"data\":\"$image_0\",\"format\":\"png\"}]},{\"images\":[{\"data\":\"$image_1\",\"format\":\"png\"}]},{\"images\":[{\"data\":\"$image_2\",\"format\":\"png\"}]},{\"images\":[{\"data\":\"$image_3\",\"format\":\"png\"}]}],\"params\":{\"output_types\":[\"dense\"]}}"
Build the "Image search" 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: http://localhost:8080, my own SIE server, which takes no API key.
- Model: Marqo/marqo-fashionSigLIP (SIE primitive: /encode). Keep the model id configurable.

Task
- Input: a text query plus one or more candidate images.
- Behaviour: return native dense vectors for the query and candidate images
- Encode the text query and candidate images together in one client.encode call, preserving the original image bytes. Return the native dense vectors without application scoring or ranking.

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.

Next to the other image and text models

Next to the other image and text models
Model Flickr30k image to text, nDCG@10 Time per request Serverless price Size
SigLIP so400m google 0.900 Not timed $0.031 per 1M tokens $0.0233 per 1,000 images 878M
CLIP ViT H 14 laion2B s32B b79K laion 0.862 Not timed Run in your cloud 986M
siglip so400m patch14 224 google 0.838 Not timed Run in your cloud 877M
siglip2 base patch16 224 google 0.816 Not timed $0.0231 per 1M tokens $0.0143 per 1,000 images 375M
All 10 image and text models

Measured on public datasets

Measured on public datasets
Dataset nDCG@10
Flickr30kI2TRetrieval Measured internally 0.838

Facts

Size
203M parameters
License
Apache-2.0
Reads
Text (up to 64 tokens), image
Endpoint
encode
Evaluation
Accuracy
Run on SIE against the public dataset named in each figure
Prices
Serverless list prices, effective 10 Nov 2026

Run marqo fashionSigLIP in your own cloud, or start on Serverless

SIE Cluster

Kubernetes in your own 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.

SIE Local

The open-source server on your own machine.

  • Runs on your 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 ghcr.io/superlinked/sie-server:latest-cuda12-default

Talk to us

Tell us about your use case and we'll get back to you shortly.

Apply for an inference grant

Free capacity on our hosted cluster for selected projects. Tell us what you run and we reply by email.