What is Baseten
Baseten provides managed model APIs, dedicated deployments and training infrastructure for production AI applications.
Plans
As of July 31, 2026, Basic costs US$0 per month plus pay-as-you-go usage and includes model APIs, training and dedicated deployments. Pro uses custom pricing and adds volume discounts, priority GPU access, dedicated compute, higher API rate limits and Slack, Zoom and support access. Enterprise is also custom priced and can add self-hosting, flexible compute, cloud-commitment support, data residency, security controls and role-based access.
Usage pricing
Current model API examples per million tokens include GPT-OSS 120B at US$0.10 input and US$0.50 output, GLM-5.2 at US$1.40 input, US$0.14 cached input and US$4.40 output, and GLM-5.2 Fast at US$2.10 input, US$0.21 cached input and US$6.60 output.
Published dedicated deployment rates per minute include US$0.01052 for T4, US$0.01414 for L4, US$0.02012 for A10G, US$0.06667 for A100, US$0.10833 for H100 and US$0.16633 for B200. Baseten says usage is billed for compute consumed without idle-time charges.
Official source: Baseten pricing.