model-router

Name: model-router
Availability: InStock
Author: winsorllc

Route LLM requests across providers with failover and dynamic rules.

1|Updated Feb 25, 2026

Search Tags:#api #routing #llm #failover #model selection #provider management

Ready to run

npx skills add https://github.com/winsorllc/upgraded-carnival --skill model-router-winsorllc

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: model-router
Source: https://github.com/winsorllc/upgraded-carnival/tree/main/.pi/skills/model-router
Command: npx skills add https://github.com/winsorllc/upgraded-carnival --skill model-router-winsorllc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill streamlines LLM interactions by intelligently routing requests to the most suitable model and provider, with automatic failover mechanisms to ensure continuous operation.

Core Features & Use Cases

Dynamic Routing: Configure rules to direct tasks (e.g., coding, research) to specific LLM providers and models.
Provider Management: Lists available LLM providers, checks their status, and manages API keys via environment variables.
Failover Support: Automatically switches to backup providers if the primary choice is unavailable.
Use Case: Ensure your AI assistant always uses the best available model for coding tasks, falling back to a more general model if the preferred one is down, without interrupting your workflow.

Quick Start

Use the model-router skill to route a research task with the prompt "Explain the latest advancements in AI".

Frequently Asked Questions about model-router

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

FAQPage Schema

How do I configure LLM routing rules to direct specific tasks to different models?▼

LLM routing rules are dynamically configured to direct specific task types, such as coding or research, to designated LLM providers and models. This ensures requests always reach the most suitable available model.

What is automatic failover for LLM API requests and how does it keep workflows running?▼

Automatic failover for LLM API requests switches traffic to backup providers if the primary choice becomes unavailable. This ensures continuous operation and prevents workflow interruptions during outages.

Can I use local Ollama instances alongside external LLM API providers for routing?▼

Yes, you can integrate and route requests between multiple external LLM APIs and local Ollama instances. This allows flexible provider management and localized model execution within your routing configuration.

How do I manage API keys for multiple LLM providers during failover setup?▼

You manage API keys for multiple LLM providers by utilizing environment variables. This approach secures credentials while allowing the routing system to access various providers during failover scenarios.

What is the best way to handle provider availability when selecting LLM models?▼

The best way to handle provider availability is by checking provider status and configuring fallback mechanisms. This dynamically selects models based on real-time availability and task type requirements.