> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bioptimus.com/llms.txt
> Use this file to discover all available pages before exploring further.

# H-Optimus

> A vision foundation model for histology feature extraction.

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](/documentation/models/m-optimus)).

<Note>
  **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](/documentation/models/benchmarks) and the [Hugging Face model details](/deployment/platforms/hugging-face).
</Note>

<Frame caption="Spatial PCA of tile embeddings on a TCGA-LUAD slide (TCGA-75-7027) — PC1–PC3 each isolate a distinct tissue region (e.g. tumor epithelium, stroma, immune infiltrate). H-Optimus and M-Optimus share the same 1536-d embedding space. Representative example.">
  <img src="https://mintcdn.com/bioptimus-79a2297b/wzVDcCnzT959rZil/images/figures/embeddings-pca-spatial.png?fit=max&auto=format&n=wzVDcCnzT959rZil&q=85&s=b025c90df2d995becf9aa8c78f139f38" alt="Spatial heatmaps of the first three principal components of tile embeddings" width="1781" height="504" data-path="images/figures/embeddings-pca-spatial.png" />
</Frame>

## Specifications

| Property             | Value                                   |
| -------------------- | --------------------------------------- |
| Task                 | Tile embedding                          |
| Input                | 224×224 RGB tile at 0.5 µm/px           |
| Output               | 1536-dimensional feature vector         |
| On-prem endpoint     | `POST /api/embed/h1`                    |
| SageMaker dispatch   | `model_name: "h1"`, `mode: "embedding"` |
| Recommended instance | `ml.g5.xlarge`                          |

## How it's used

<Steps>
  <Step title="Segment tissue">
    Run [tissue segmentation](/documentation/models/tissue-segmentation) to keep tissue-bearing tiles.
  </Step>

  <Step title="Extract features">
    Embed 224×224 tiles to get a 1536-d vector each (the [SDK](/guides/get-started/sdk) tiles and dispatches for you).
  </Step>

  <Step title="Build downstream models">
    Aggregate embeddings for slide-level prediction, retrieval, or classification.
  </Step>
</Steps>

## Deploy

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

## Guides

<CardGroup cols={2}>
  <Card title="Tile embeddings & PCA" href="/guides/workflows/embeddings-pca">
    Extract embeddings and visualize morphology.
  </Card>

  <Card title="Bioptimus SDK" href="/guides/get-started/sdk">
    Run whole-slide inference with the Bioptimus SDK.
  </Card>
</CardGroup>