Ginkgo launched a protein language model and Model API with Google Cloud.
Drug developers had limited access to advanced AI tools for protein analysis and design. Ginkgo released a protein LLM through Google Cloud Vertex AI Model Garden and an open API serving ginkgo-AA-0-650m, trained on over 2 billion proprietary protein sequences. The page quotes about $0.18 per million tokens, or roughly 10 cents for predictions on 2,000 sequences.
Ginkgo Bioworks is a synthetic biology platform company that sells lab data generation and biological AI models, including Datapoints and a Model API built with Google Cloud.
This sits in the Build stage of the AI use-case lifecycle: Named examples from the foundation-model labs and platforms pharma teams use to actually construct, train and generate the model or application.
Published by Ginkgo Bioworks on its own site — read the original case study on googlecloudpresscorner.com ↗
Related use cases
- 01Ginkgo Datapoints partnered with Lilly TuneLab to link AI models to lab data.
- 02OpenAI's dedicated healthcare vertical page/launch post.
- 03Frontier reasoning model built for biology, drug discovery and translational medicine; named qualified customers include Amgen, Moderna, Allen Institute, and Thermo Fisher Scientific.
- 04follow-up update to the life-sciences model.
- 05"How Amgen uses GPT-5": Amgen applies GPT-5/frontier models to help accelerate delivery of potential new therapies; found GPT-5 met scientific-accuracy standards.
- 06Moderna and OpenAI partner to accelerate development of treatments; ChatGPT Enterprise deployed to thousands of employees company-wide.