AI Gateway

Create API keys to authenticate requests to AI Gateway. You can also inspect virtual model configurations to see how your model endpoints are configured.

`create_api_keys`

Create an AI Gateway API key.

Parameters

Parameter	Type	Required	Description
`requestBody`	object	No	Request body for this tool.
`teamId`	string	No	Team ID.

`get_ai_gateway_virtual_model_config`

Get virtual model config.

Parameters

Parameter	Type	Required	Description
`ownerId`	string	No	-
`virtualModelSlug`	string	Yes	The virtual model slug.
`teamId`	string	No	Team ID.
`slug`	string	No	Team slug.

Cross-link map: AI Gateway (/docs/agent-resources/vercel-mcp/tools/ai-gateway)

From the Vercel docs graph (built 2026-10-06T09:42:32.185Z), spanning vercel.com docs + KB, nextjs.org, ai-sdk.dev, and other Vercel documentation sites. Full graph as JSON: https://vercel.com/docs/graph.json

Semantically closest pages

get_ai_gateway_virtual_model_config — Use get_ai_gateway_virtual_model_config with Vercel MCP.
create_api_keys — Use create_api_keys with Vercel MCP.
Vercel AI Gateway: Models, Routing, and Observability — Call AI models from any infrastructure through a managed gateway. Centralize credentials, request logs, spend budgets, r
Getting Started with AI Gateway — Set up AI Gateway with a coding agent, route the agent through AI Gateway, or make your first request with cURL, TypeScr
Pydantic AI with AI Gateway — Learn how to integrate Vercel AI Gateway with Pydantic AI to access multiple AI models through a unified interface.

Prerequisites

Agent Resources — Set up AI coding tools with Vercel documentation, reusable skills, and secure access to projects, deployments, and logs.

Agent Runs

create_api_keys

Was this helpful?