From the source
From the source
Vercel Ship 2025 recap: AI Gateway, Fluid compute, Active CPU pricing, Sandbox, and Rolling Releases
Vercel announced several platform updates at Ship 2025, including AI Gateway for unified model access across providers, Fluid compute with Active CPU pricing that charges only for actual execution time, Vercel Sandbox for running untrusted code in isolated microVMs, and Rolling Releases for safe incremental deployments.
The default execution time for all projects using Fluid compute increased to 300 seconds.
From the source
Active CPU charges for the time your code is actually executing. Provisioned Memory covers the time your function is waiting, charged at 1/11th the rate. Invocations counts per function call (just like in traditional serverless). If your AI call takes 30s to respond, but only uses 300ms of compute, you only pay for those 300ms.
vercel.com
