ai-gateway

Route AI model calls across providers with failover and cost tracking.

1|Updated Apr 17, 2026
One-click install
npx skills add https://github.com/esneiderbravo/hackaton --skill ai-gateway-esneiderbravo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai-gateway
Source: https://github.com/esneiderbravo/hackaton/tree/main/.github/skills/ai-gateway
Command: npx skills add https://github.com/esneiderbravo/hackaton --skill ai-gateway-esneiderbravo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Unifies AI model routing, failover, and cost tracking across multiple providers behind a single API, simplifying governance and observability.

Core Features & Use Cases

  • Unified provider routing: route model calls using a provider/model string through the gateway to simplify integration.
  • Automatic failover and cost controls: automatically switch providers on failure and attribute usage to users via tags.
  • Per-user telemetry and auditing: support for per-user rate limits, budgets, and audit logs for multi-tenant environments.

Quick Start

Configure a route by providing a provider/model string and enabling gateway options such as order and tags.

Frequently Asked Questions about ai-gateway

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I route requests to multiple AI providers through a single API?

You can route requests to multiple AI providers by using a provider/model string through a unified AI gateway. This simplifies integration by managing all model calls behind a single API endpoint.

What is the best way to track per-user AI model costs in a multi-tenant environment?

The best way to track per-user AI model costs is by using an AI gateway with per-user tagging. This allows you to attribute usage accurately and enforce per-user rate limits and budgets across your teams.

How does automatic failover work for AI model routing?

Automatic failover for AI model routing works by automatically switching providers when a failure occurs. The gateway detects the issue and reroutes the model call to another available provider to ensure continuity.

Can I use OIDC for authentication when routing model calls through an AI gateway?

Yes, you can use OIDC for authentication when routing model calls through an AI gateway. It provides secure access control and supports per-user telemetry and auditing in multi-tenant environments.

How do I set up audit logs for AI model usage across different product teams?

You can set up audit logs for AI model usage by routing traffic through an AI gateway that supports per-user telemetry. This captures detailed usage data, enabling auditing and governance across product teams.