Skip to content

Model Labs

Bioptimus

Biology foundation-model company behind the H-optimus histopathology models.

Histopathology embeddings1 model

Models on Rafflesia

H-optimus-0

previewApache-2.0
bioptimus/h-optimus/0/embed

Create pooled tile-level histopathology representations with the 1.1B-parameter H-optimus-0 vision transformer trained on H&E-stained whole-slide image tiles.

Histopathology embeddingshistopathology_image → embedding_vector
$0.0005 / image

About

Bioptimus builds multi-scale foundation models for biology. Its first open-weight release, H-optimus-0, is a 1.1B-parameter vision transformer trained with self-supervision on hundreds of millions of H&E histopathology tiles drawn from over 500,000 slides.

On Rafflesia, H-optimus-0 is served for tile-level histopathology feature extraction via the runs API through the same provider/family/variant endpoint convention as the sequence models.

Use these models

Every endpoint speaks the same run lifecycle: POST the endpoint id and a typed input, get a run back with outputs, provenance, and measured billing.

run.sh
# one run lifecycle, every endpoint
curl https://api.rafflesia.ai/v1/runs \
  -H "Authorization: Bearer $RAFFLESIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
        "endpoint": "bioptimus/h-optimus/0/embed",
        "input": { "sequence": "MKTAYIAK..." }
      }'
Read the quickstartOpen the dashboard