What problem does it solve? Integrating multiple AI model providers requires juggling separate SDKs, API keys, billing accounts, and failover logic. This Skill guides you through Vercel AI Gateway so you can access models from many providers through one authenticated endpoint with unified routing, spend controls, and request logging. ## Core Features & Use Cases - Setup & Authentication: Configure AI Gateway API keys or Vercel OIDC tokens, migrate existing OpenAI or Anthropic SDK integrations by changing the base URL, and handle BYOK provider credentials correctly. - Model Discovery & Routing: Fetch the live model catalog from /v1/models, choose models by modality, capability, price, or data retention, and configure provider ordering, model fallbacks, prompt caching, and reasoning settings. - Spend Controls & Observability: Set budgets at team, project, API key, or user scope, query credit balances and per-generation costs, and debug requests through AI Gateway Logs. - Use Case: You have an app calling the OpenAI SDK directly. Use this Skill to repoint its base URL to the gateway, pick a current model ID, add a fallback model, and set a monthly budget on the API key. ## Quick Start Ask the agent to add Vercel AI Gateway to your app and make one authenticated test request using a model from the live /v1/models list.
