Skip to content

Model Labs

Meta AI

Creator of the ESM protein language model family.

Protein embeddings2 models

Models on Rafflesia

ESM-2 8M

activeMIT
meta-ai/esm2/8m/embed

Create pooled or residue-level protein representations with the 6-layer, 8M-parameter ESM-2 checkpoint.

Protein embeddingsprotein_sequenceembedding_vector
$0.0001 / 1K residues

ESM-2 35M

activeMIT
meta-ai/esm2/35m/embed

Create pooled or residue-level protein representations with the 12-layer, 35M-parameter ESM-2 checkpoint.

Protein embeddingsprotein_sequenceembedding_vector
$0.00025 / 1K residues

About

Meta AI's fundamental AI research group created the ESM family of protein language models, whose open weights became foundational infrastructure for protein machine learning.

On Rafflesia, the CPU-served ESM-2 embedding models are addressed explicitly at 8M and 35M parameters through the same provider/family/variant endpoint convention.

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": "meta-ai/esm2/8m/embed",
        "input": { "sequence": "MKTAYIAK..." }
      }'