DockingGPU15 credits

Boltz-2 — Complex Prediction

Predict biomolecular complex structures: protein, ligand, DNA, RNA

Boltz-2 predicts the 3D structure of biomolecular complexes including protein-protein, protein-ligand, protein-DNA, and protein-RNA interactions. It's an open-source alternative to AlphaFold3 for multi-chain structure prediction.

$0.15

per API call

credits per call

/v1/docking/boltz2

API endpoint

Features

Multi-chain complex prediction

Supports protein, DNA, RNA, and small molecules

GPU-accelerated on NVIDIA A100

Up to 5 models per prediction

Confidence scores for each prediction

Open-source model weights

Quick Start

Boltz-2 — Python Examplepython

import requests

API_KEY = "sk-sci-your-key-here"
url = "https://scirouter.ai/v1/docking/boltz2"

response = requests.post(url, json={
    "chains": [
        {"type": "protein", "sequence": "MKFLILLFN..."},
        {"type": "protein", "sequence": "MAEGEITTF..."},
        {"type": "smiles", "sequence": "CC(=O)Oc1ccccc1C(=O)O"}
    ],
    "num_models": 3
}, headers={"Authorization": f"Bearer {API_KEY}"})

job = response.json()
# Poll for results with job_id...