Baseten

Baseten is an inference platform for teams that run AI models in production. It provides the infrastructure, tooling and engineering support to serve open-source, custom and fine-tuned models at scale, with a focus on fast runtimes, reliability and developer workflows.

The product set includes dedicated inference for high-scale workloads, pre-optimized model APIs for testing new models, a model library, and a training option that uses a Loops SDK for reinforcement learning with deployment on the same stack. Cross-cloud high availability is a selling point, and the company describes performance work that includes custom kernels and advanced decoding techniques. Baseten for Model Labs lets model creators distribute and monetize models on its infrastructure.

Baseten is a proprietary commercial service with a pricing page, documentation and an option to talk to an engineer. It is aimed at AI product companies that want production inference without running their own GPU fleets.