Introducing Active CPU pricing for Fluid compute
Up to 85% cost cuts. Vercel's new Active CPU pricing charges only when your inference code actually runs—not idle time.
Why it matters
As AI inference workloads scale, serverless pricing models that charge for idle time become prohibitively expensive. Vercel's Active CPU pricing directly addresses the economics of long-running AI agents and inference backends, making real-time AI deployments more cost-competitive.
The key facts
11 to knowVercel launches Active CPU pricing for Fluid compute
Up to 85% cost savings claimed through optimizations like in-function concurrency
Targets I/O-bound workloads: AI inference, agents, MCP servers
Pay-per-active-CPU model (not idle-time billing)
Designed for long-running, unpredictable workloads
Published June 25, 2025
Up to 85% cost savings through optimizations like in-function concurrency
New pricing model: pay CPU rates only when code actively uses CPU
Targets I/O bound backends: AI inference, agents, MCP servers
Addresses long-running, unpredictable workloads with frequent idle periods
Fluid Compute became default model on Vercel
Go to the source
Vercel Blogvercel.com
Publisher excerpt: exists for a new class of workloads. I/O bound backends like AI inference, agents, MCP servers, and anything that needs to scale instantly, but often remains idle between operations. These workloads do not follow traditional, quick request-response patterns. They’re long-running, unpredictable, and…