BoltzFold

Queue Protein folding predictions, monitor progress, and download structures.

commoditize protein folding

One API for ESMFold (fast), OpenFold (accurate, coming), and Boltz-2 (protein-ligand). EU-hosted, privacy-first, reproducible by default.

Start folding → Talk to us

Used by early teams at

•Your Lab••Your pharma company••Your uni•

How it works

1) Submit

POST /v1/predict with a FASTA (and SMILES for ligand). Or use the web UI.

2) We route

Auto-select the best model for speed vs accuracy (or pin one). Jobs run asynchronously on dedicated GPUs.

3) Download

Get .pdb/.cif, confidence (pLDDT/PAE), and affinity (Boltz-2). Every job includes a reproducibility manifest.

Why teams switch to us

Multi-model, one endpoint

ESMFold fast, OpenFold accurate (soon), Boltz-2 for protein–ligand. Route automatically or have full control if you want.

Predictable costs

Per-residue pricing, cache re-use, and budget guardrails.

Private by design

EU data residency, zero-retention mode, audit logs, signed manifests.

Developer-first

Simple REST, Python/JS SDKs, webhooks, standardized outputs.

What's under the hood

FAQ

How fast are results?

Minutes. ESMFold often < 2 min; OpenFold 3–10; Boltz-2 5–15 depending on length/steps.

Is it license-safe for commercial use?

Yes — the models/weights we serve (ESMFold, OpenFold, Boltz-2) permit commercial use with attribution where required.

Can I pick the model?

Yes. Use mode=auto or pin a backend explicitly.

Where does my data live?

EU by default. Zero-retention mode and VPC/on-prem options on request.

For investors

We're standardizing structure prediction into a developer-first primitive: a license-clean, EU-native folding substrate that routes across models and returns publishable outputs. An API for developers and a web UI for researchers.

Request our deck