Skip to content
All tool news

Tool desk · Updated daily

Tool news·Vercel·

Vercel Virtual Models Centralise AI Gateway Configuration.

Vercel virtual models let builders manage AI Gateway model IDs, configurations and Zero Data Retention from one place.

CW

Create With tool desk

4 sources checked · 2 min read · 3 sections

ShareLinkedIn
Vercel Virtual Models Centralise AI Gateway Configuration

Vercel’s virtual models let builders use one model ID across multiple agents, then manage the underlying model strings and configurations centrally through AI Gateway.

The change removes the need to edit each agent when switching models or changing a shared configuration. According to the LinkedIn announcement, teams can also use virtual models to enforce Zero Data Retention across their agents.

How Vercel virtual models work

Each agent can reference the same virtual model ID rather than carrying its own model string and configuration. The model behind that shared ID can then be changed centrally.

That gives teams one control point for model updates. When a new model becomes the preferred option, the virtual model can be updated immediately instead of replacing model IDs across every agent that uses it.

TaskSeparate model IDsVirtual model ID
Set the modelConfigure each agentManage the shared model centrally
Change modelsUpdate affected agentsUpdate the virtual model
Manage configurationsMaintain them across agentsControl them centrally
Apply Zero Data RetentionHandle it across implementationsEnforce it through the virtual model

The virtual ID also separates an agent’s reference from the underlying model string. Agents continue using the same ID while the centrally managed model or configuration changes.

One place for model controls

Virtual models cover three jobs in the announcement: managing model strings, managing configurations and enforcing Zero Data Retention. All three sit behind the same virtual model ID used by connected agents.

This is particularly relevant when several agents share a model policy. A change no longer requires the model reference to be found and replaced in each agent individually. The shared virtual model becomes the place where that change is made.

It also provides a direct route for model upgrades. Teams can point the virtual model at a newer model without changing the ID already used across their agents.

Virtual models add a management layer to Vercel’s AI Gateway rather than changing the individual agents themselves. The agents use the shared identifier, while the model selection and associated controls are maintained in one place.

Frequently asked questions

What are Vercel virtual models?

Virtual models are shared AI Gateway identifiers that multiple agents can use. They let teams centrally manage the model strings and configurations behind those identifiers.

Can virtual models enforce Zero Data Retention?

Yes. Zero Data Retention enforcement is one of the controls included in Vercel’s announcement, alongside central management of model strings and configurations.

Which Vercel plan includes virtual models?

The announcement does not give pricing or plan availability for virtual models. It introduces the feature as part of AI Gateway.

Sources

4 checked

How we cover tool news: Create With's tool desk drafts these reports with AI from the sources listed above and checks them against those sources before publishing.

Worth passing on?

ShareLinkedIn

Go deeper on Vercel

Related reading, watching and going.

Everything on Vercel →

The briefing

19 May 2026

How to Migrate Your App from Lovable to Claude Code in 2025

Step-by-step guide to migrating your Lovable app to Claude Code. Learn how to move from Lovable's managed platform to a stack you own and control.

Read →

The briefing

10 Feb 2026

OpenClaw Review: 2 Weeks With This AI Agent

Honest 2-week review of OpenClaw — an autonomous AI agent powered by Claude. We test setup, safety, autonomy, and real value to see if it's worth using.

Read →
34 min

Podcast

My Daughter Built a Website Business, Claude Design First Look & Going All-In on Cloudflare

James and Kieran discuss practical AI-powered development through real-world examples, including a seven-year-old building a website business with Claude Code voice mode, Anthropic's new Claude Design tool, API security challenges in the AI agent era, and Cloudflare's expanding AI infrastructure offerings. The episode covers hands-on experiences with vibe coding, emerging design tools, and the evolving landscape of AI-assisted development.

Watch now ↗

Podcast

53. Why Your Vibe Code Needs Tests, Ditching SaaS & AI Agents That Work While You Sleep

James and Kieran discuss the practical realities of building AI-powered software, emphasizing the importance of testing in vibe-coded applications, exploring alternatives to traditional SaaS tools, and implementing autonomous AI agents for business operations. The episode covers technical topics like Convex databases, app store bottlenecks from AI-generated submissions, and using OpenClaw as a marketing automation agent.

Watch now ↗
38 min

Podcast

52. Your AI Co-Founder: OpenClaw, Manus & the Zero-Person Business

In this Create With podcast episode, James and Kieran are joined by Matt Roberts from Happy Operators for an in-depth discussion on using autonomous AI agents in production. The conversation covers practical experiences with OpenClaw, security considerations, comparison with emerging tools like Manus, and the broader shift toward AI-assisted development. They also discuss the VibeCoding Olympics results, Bubble's new AI capabilities, and research on Claude.MD file effectiveness.

Watch now ↗

Latest tool news

What else changed this week.

All tool news

The Create With Briefing

Don't watch forty changelogs. Read one email.

Every Tuesday: the tool changes worth knowing, real business use cases, and what's on near you. Free, unsubscribe any time.