openrouter-model-routing
Implement advanced model routing with A/B testing. Use when optimizing model selection or running experiments. Trigger with phrases like 'openrouter a/b test', 'model experiment', 'openrouter routing', 'model comparison'.
When & Why to Use This Skill
The OpenRouter Model Routing skill provides a sophisticated framework for managing and optimizing Large Language Model (LLM) selection. It enables developers to implement advanced orchestration patterns such as A/B testing, performance-based routing, and gradual rollouts. By leveraging this skill, users can dynamically balance cost, latency, and intelligence, ensuring that each request is handled by the most appropriate model while maintaining high system reliability.
Use Cases
- LLM A/B Testing: Compare the output quality and accuracy of different models (e.g., Claude vs. GPT) in real-time to identify the best fit for specific use cases.
- Dynamic Cost Optimization: Implement logic to route routine or simple tasks to cost-effective, lightweight models while reserving complex reasoning for premium, high-tier models.
- Canary Deployments and Gradual Rollouts: Safely introduce new model versions to a small percentage of traffic to monitor performance and stability before a full-scale migration.
- High Availability and Failover: Configure automated routing to backup providers or alternative models to ensure service continuity during API outages or rate-limiting events.
| name | openrouter-model-routing |
|---|---|
| description | | |
| allowed-tools | Read, Write, Edit, Grep |
| version | 1.0.0 |
| license | MIT |
| author | Jeremy Longshore <jeremy@intentsolutions.io> |
OpenRouter Model Routing
Overview
This skill covers advanced routing patterns including A/B testing, gradual rollouts, and performance-based model selection.
Prerequisites
- OpenRouter integration
- Metrics collection capability
Instructions
Follow these steps to implement this skill:
- Verify Prerequisites: Ensure all prerequisites listed above are met
- Review the Implementation: Study the code examples and patterns below
- Adapt to Your Environment: Modify configuration values for your setup
- Test the Integration: Run the verification steps to confirm functionality
- Monitor in Production: Set up appropriate logging and monitoring
Overview
This skill covers advanced routing patterns including A/B testing, gradual rollouts, and performance-based model selection.
Prerequisites
- OpenRouter integration
- Metrics collection capability
Intelligent Model Selection
Multi-Criteria Router
from dataclasses import dataclass
from typing import Callable, Optional
import re
@dataclass
class ModelProfile:
id: str
## Detailed Reference
See `{baseDir}/references/implementation.md` for complete implementation guide.