# Introducing Virtual Models on AI Gateway

Source: [Vercel](https://vercel.com/blog/ai-gateway-virtual-models)  
Feed7 permalink: https://feed7.dev/p/ai-gateway-virtual-models-0563pz8  
Published: 2026-10-28T07:25:00.000Z  
Trust: Official Source (official_source)

## Why Included

Vercel AI Gateway Virtual Models let agents use a stable task ID while teams change models, routing, and compliance settings centrally. Run evals against a candidate before switching a production task.

## Source Summary

Virtual Models give a task a stable model ID, such as **vmc/coding-agent**, while AI Gateway centrally controls its model, fallbacks, priority, and Zero Data Retention settings. Changes propagate to callers within minutes without code changes or redeploys.

## Practical Implication

For coding agents, assign IDs by task and use a candidate virtual model to run evals before changing production. Team roles control who can edit configurations, and callers cannot override centrally set routing or data-retention requirements.

## Agent-Ready Context

Virtual Models give a task a stable model ID, such as **vmc/coding-agent**, while AI Gateway centrally controls its model, fallbacks, priority, and Zero Data Retention settings. Changes propagate to callers within minutes without code changes or redeploys.

For coding agents, assign IDs by task and use a candidate virtual model to run evals before changing production. Team roles control who can edit configurations, and callers cannot override centrally set routing or data-retention requirements.

Provider-specific options stop applying when the underlying provider changes, so review settings during a switch. The article recommends testing candidates but does not specify a standard evaluation method.

## Context Map

- Layer: infra
- Domains: coding, data
- Topics: gateways, model-selection, agent-evals

## Uncertainty

- Provider-specific options stop applying when the underlying provider changes, so review settings during a switch. The article recommends testing candidates but does not specify a standard evaluation method.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.