Virtual models now available on Vercel AI Gateway
Vercel AI Gateway now supports virtual models, which are saved configurations that specify which underlying model and settings to use. Apps and agents call a virtual model by a custom ID in the form vmc/<slug>, and its model or settings can be changed centrally without redeploying apps or reconfiguring agents.
Why it matters
Builders can change the model or request settings (such as reasoning effort, fast mode, prompt caching, provider routing, Zero Data Retention, and spend tags) in one place instead of editing each app or coding agent configuration.
Who should care
Developers building AI-powered apps or agents on Vercel, teams managing AI spend or compliance requirements, and users of coding agents.
What you can do
In the AI Gateway Virtual Models page, create a virtual model with a slug, choose an underlying model, configure settings, and replace the provider model ID in an AI SDK request with vmc/<slug>.