Baseten

About Baseten

Baseten is an inference platform for deploying AI models in production. It provides dedicated inference, pre-optimized model APIs, training, and model distribution for companies building generative AI applications.

Baseten is an inference platform that deploys AI models in production. It provides high-performance model runtimes, cross-cloud high availability, and developer workflows for building AI products.

The platform offers dedicated inference for high-scale workloads, pre-optimized model APIs, training via the Loops SDK, and a Model Labs product for distributing and monetizing models. Customers can deploy open-source, custom, or fine-tuned models on Baseten's infrastructure, or self-host in their own VPCs.

Baseten serves AI companies such as Abridge, Cursor, Lovable, Notion, OpenEvidence, and Writer, which rely on it for mission-critical AI workloads. The company has raised a $1.5B Series F round.