Benchling and Baseten Partner to Bring AI Inference to Biotech R&D
Summary
Benchling and Baseten launched Benchling Inference to give biotech teams scalable, cost-effective GPU capacity to train and run scientific models without managing infrastructure. The service ships preloaded with leading scientific models and runs on Baseten's Inference Stack, which offers optimized runtimes and inference-ready infrastructure across 15+ cloud providers with fast cold starts. Benchling adds biotech-specific defaults, deployment options for strict data residency, and integrations so teams can deploy third-party or internal models and call inference from Jupyter or via an SDK. The offering aggregates industry demand to lower costs for startups and addresses bursty drug-discovery workloads that create HPC backlogs and idle GPU reservations.
