Skip to content
← Models
ClosedChai Discovery/10 trustVerified

Chai-2

Generative AI for de novo antibody design with experimental validation.

Visit official page →

About

Chai-2 is Chai Discovery's generative AI system for designing new antibodies, nanobodies, and small protein binders against a chosen protein target. Introduced June 30, 2025, it combines molecular structure prediction with sequence and structure generation, and the launch study reported binders for roughly half of 52 tested targets after assaying at most 20 designs per target, a double-digit hit rate the company describes as a hundred-fold improvement over prior computational approaches.

Chai-2 is a closed platform accessed through partnerships rather than public weights, and it has signed collaborations with Eli Lilly, Pfizer, Novartis, argenx, and GSK, with a Chai-3 successor announced for pharma partners. The honest picture: the hit-rate figures come from company preprints rather than peer-reviewed independent replication, and a binding hit is still far from a medicine, but the wet-lab validation bar it cleared is what separates it from pure benchmark claims.

Specs

Context window

Pricing

Free quota

API access

Weights

Closed — API only

Released

June 30, 2025

Benchmarks

Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.

Use cases

antibody-designdrug-discoveryprotein-engineeringbiologics

Trust score — 8/10

/10 trustVerified

Scored 8/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 95; Trending score 78/100 from researcher assessment.

More in the chai family

Sources