# Boltz-1 / Boltz-2 (MIT, open)

Source: https://onco.cc/technologies/boltz/  
OnCo record `boltz` (Technology). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Open-source structure models that match AlphaFold 3, with Boltz-2 also predicting how strongly a drug binds.

## Summary

Boltz is an open-source family of diffusion-based structure models from MIT that reproduces AlphaFold 3-level accuracy for proteins, nucleic acids and small molecules. Boltz-1 (2024) was released under the permissive MIT licence, giving academic and commercial groups a freely usable alternative to closed models. Boltz-2 (2025), developed with Recursion, added an affinity head that predicts how strongly a small molecule binds, approaching the accuracy of physics-based free energy perturbation (FEP) at a fraction of the compute cost, which matters for ranking candidate cancer drugs. Affinity accuracy varies by target class, so predictions still need experimental confirmation for a new protein family. For a newcomer: Boltz is the free model that matches AlphaFold 3 and can also estimate how tightly a drug will bind.

## Fields

- Kind: Technology
- Status: emerging
- Last checked: 2026-09-08
- Tags: foundation-model; structure
- Principle: Diffusion structure model with affinity head.
- Since: 2024
- Strengths: Open; Affinity prediction
- Limitations: Affinity accuracy varies by target class

## Sources

- Boltz-1 bioRxiv 2024: https://www.biorxiv.org/content/10.1101/2024.11.19.624167v1

## Connected records

- fronts: [AI & Computation](https://onco.cc/fronts/ai-computation/), [Drug Discovery Platforms](https://onco.cc/fronts/drug-discovery/)
- technologies: [AI-driven drug & target discovery](https://onco.cc/technologies/ai-drug-design/)
- companies: [Recursion Pharmaceuticals](https://onco.cc/companies/recursion/)
- institutions: [Broad Institute of MIT and Harvard](https://onco.cc/institutions/broad-institute/)
- roadmaps: [AI in oncology roadmap: pattern readers → foundation models → agents in the workflow](https://onco.cc/roadmaps/ai-oncology-roadmap/), [Drug discovery roadmap: screening in mice → maps of dependency → designing in silico](https://onco.cc/roadmaps/drug-discovery-roadmap/), [Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell](https://onco.cc/roadmaps/virtual-cell/)

---
JSON: https://onco.cc/api/v1/entities/boltz.json