Skip to main content
H-Optimus is a vision transformer foundation model for histology. It extracts tile-level feature vectors (embeddings) from H&E whole slide images — the input to downstream tasks such as mutation prediction, survival analysis, and tissue classification. H-Optimus produces features; it does not predict molecular signal directly (for that, see M-Optimus).
H-Optimus-1 is current — a 1.1B-parameter vision transformer (ViT-g/14) trained with self-supervised learning on billions of tiles from over 1 million slides of more than 800,000 patients, spanning 50+ organs, 3 scanner types, and 4,000+ clinical centers. As of May 2026 it ranks #1 on the public PathBench leaderboard and is the top image-only model on HEST. H-Optimus-0 (2024) is the previous generation, open-source under Apache 2.0. See Benchmarks and the Hugging Face model details.
Spatial heatmaps of the first three principal components of tile embeddings

​
Specifications

PropertyValue
TaskTile embedding
Input224×224 RGB tile at 0.5 µm/px
Output1536-dimensional feature vector
On-prem endpointPOST /api/embed/h1
SageMaker dispatchmodel_name: "h1", mode: "embedding"
Recommended instanceml.g5.xlarge

​
How it’s used

1

Segment tissue

Run tissue segmentation to keep tissue-bearing tiles.
2

Extract features

Embed 224×224 tiles to get a 1536-d vector each (the SDK tiles and dispatches for you).
3

Build downstream models

Aggregate embeddings for slide-level prediction, retrieval, or classification.

​
Deploy

H-Optimus runs on AWS SageMaker, on-premise, or Hugging Face (academic). See the Deployment overview for the full comparison and setup steps.

​
Guides

Tile embeddings & PCA

Extract embeddings and visualize morphology.

Bioptimus SDK

Run whole-slide inference with the Bioptimus SDK.