Baseten provides a platform for high-performance inference. It delivers the fastest model runtimes, cross-cloud high availability, and seamless developer workflows all powered by the Baseten Inference Stack. Baseten offers 3 core products: - Dedicated inference - to serve open-source, custom, and fine-tuned AI models on infrastructure purpose-built for high performance inference at massive scale. - Models APIs - to test new workloads, prototype products for evaluate the latest models optimized to be the fastest in production. - Training - to train models and easily deploy them in one click on inference-optimized infrastructure for the best possible performance. Developers using Baseten can choose from 3 deployment options depending on their needs. - Baseten Cloud to run production AI across any cloud provider with ultra-low latency, high availability, and effortless autoscaling. - Baseten Self-Hosted to run product AI at low latency and high throughput in the customer's own VPC. - Baseten Hybrid delivers the performance of a managed service in the customer's VPC with seamless overflow to Baseten Cloud.