skip to content
gigarouter gigarouter
models / zero-shot image · coming soon

SigLIP 2 Base

google/siglip2-base-patch16-256

published Feb 2025 · updated Feb 2025

SigLIP 2 Base is a zero-shot-image model that extends the SigLIP pretraining objective with captioning, self-supervised losses, and online data curation for improved semantic understanding, localization, and dense features.

est. price
~$0.094
/ 1k images · estimated, set at launch
API providers
0
downloads / mo
212.4K
license
apache-2.0

specs

TaskZero-Shot Image Classification, Image-Text Retrieval, Vision Encoder
ArchitectureViT-B/16 (Vision Transformer Base, patch size 16)
Parameters86M
LicenseApache 2.0

about this model

SigLIP 2 Base is a vision-language encoder model for zero-shot image classification and image-text retrieval, built on the SigLIP framework with an extended training recipe that improves semantic understanding, localization, and dense feature extraction. With 86 million parameters, it is designed for efficient inference while maintaining strong performance across a range of vision-language tasks.

The model is pre-trained on the WebLI dataset and further refined using a diverse multilingual data mixture with de-biasing techniques, resulting in better multilingual understanding and fairness. The training incorporates captioning-based pretraining, self-supervised losses (self-distillation, masked prediction), and online data curation. SigLIP 2 also supports multiple input resolutions and preserves the native aspect ratio of images during inference.

Benchmark Performance

On standard zero-shot and retrieval benchmarks, the 256px base variant achieves the following results:

BenchmarkMetricScore
ImageNetZero-shot top-1 accuracy79.1%
COCO (text-to-image)Recall@153.2
COCO (image-to-text)Recall@169.7

Further evaluation results from the paper are shown below:

Evaluation table comparing SigLIP 2 performance across multiple benchmarks including zero-shot classification, retrieval, and dense prediction tasks.

Compared to the original SigLIP, the new training recipe yields substantial gains on localization and dense prediction tasks, including semantic segmentation, depth estimation, and referring expression comprehension. The model also serves as a drop-in vision encoder for Vision-Language Models (VLMs), offering improved transfer performance at no additional inference cost.

best for

FAQ

What is the input format for the API?

The API accepts an image URL or base64-encoded image and a list of candidate text labels for zero-shot classification, or an image and text pair for retrieval.

How do I call this model via the gigarouter API?

Use the gigarouter OpenAI-compatible endpoint with your API key, sending a POST request with the image and text inputs in the required format.

What is the model's zero-shot ImageNet accuracy?

SigLIP 2 Base (B/16, 256px) achieves 79.1% zero-shot accuracy on ImageNet.

What license is this model released under?

The model is released under the Apache 2.0 license.

How does SigLIP 2 Base compare to the original SigLIP Base?

SigLIP 2 Base outperforms the original SigLIP Base on zero-shot classification, image-text retrieval, and dense prediction tasks, with improved multilingual understanding and fairness.

not yet live

We're benchmarking and onboarding SigLIP 2 Base as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.

related zero-shot image models

compare all →