ProteinsGPU2 credits

Protein Embeddings — ESM-2

Generate protein language model embeddings for ML tasks

Generate high-dimensional protein embeddings using Meta's ESM-2 language model. These embeddings capture structural and functional information for downstream machine learning tasks like classification, clustering, and similarity search.

$0.02

per API call

credits per call

/v1/proteins/embeddings

API endpoint

Features

768-dimensional embeddings from ESM-2

Captures structural and functional information

GPU-accelerated inference

Per-residue and mean-pooled embeddings

Compatible with standard ML frameworks

Batch processing support

Quick Start

ESM-2 — Python Examplepython

import requests
import numpy as np

API_KEY = "sk-sci-your-key-here"
url = "https://scirouter.ai/v1/proteins/embeddings"

response = requests.post(url, json={
    "sequence": "MKFLILLFNILCLFPVLAADNHGVS..."
}, headers={"Authorization": f"Bearer {API_KEY}"})

data = response.json()
embedding = np.array(data["embedding"])
print(f"Embedding shape: {embedding.shape}")  # (768,)