One-click install
npx skills add https://github.com/OpenRouterTeam/skills --skill openrouter-models-openrouterteam
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openrouter-models
Source: https://github.com/OpenRouterTeam/skills/tree/main/skills/openrouter-models
Command: npx skills add https://github.com/OpenRouterTeam/skills --skill openrouter-models-openrouterteam

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Manually tracking OpenRouter's frequently updated model catalog, pricing, and provider performance metrics is time-consuming and error-prone, especially when evaluating options for specific use cases like coding, image generation, or low-latency deployments.

Core Features & Use Cases

  • Model Discovery & Search: List all available models, filter by category (e.g. programming, vision) or modality, and search by name to find the right fit for your task.
  • Model Comparison: Side-by-side comparison of pricing, context length, supported parameters, and capabilities for multiple models to identify the best value.
  • Provider Performance Evaluation: Check per-provider latency, uptime, and throughput for any model to select the fastest or most reliable hosting option.
  • Fuzzy Name Resolution: Convert informal model names like "claude sonnet" or "gpt 4o mini" to exact OpenRouter model IDs automatically.

Quick Start

Use the openrouter-models skill to find the cheapest image-capable model available for your design project.

Frequently Asked Questions about openrouter-models

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

FAQPage Schema
How do I compare OpenRouter AI model pricing and context lengths for specific use cases?

Model comparison uses real-time metadata retrieval for 300+ OpenRouter AI models to evaluate pricing, context lengths, and supported parameters side-by-side. This identifies the best value and optimal fit for specific tasks like coding or image generation.

Can I resolve informal AI model names like "claude sonnet" to exact OpenRouter IDs automatically?

Fuzzy name resolution automatically converts informal names like "claude sonnet" or "gpt 4o mini" to exact OpenRouter model IDs. This eliminates manual lookup errors when searching for specific AI models during endpoint selection.

What's the best way to check OpenRouter provider latency and uptime before deploying an AI model?

Evaluating provider performance involves retrieving live metrics for per-provider latency, uptime, and throughput. Checking these hosting metrics helps identify the fastest and most reliable OpenRouter endpoint options for low-latency deployments.

How do I filter OpenRouter models by modality to find options for vision or programming tasks?

Model search and discovery allows filtering OpenRouter models by modality or category, such as programming or vision, to find the right fit. It retrieves real-time metadata ensuring you find the optimal AI model for your specific task requirements.

Does this OpenRouter model search require external dependencies to access live provider metrics?

No external dependencies are required to access live provider metrics or perform model search. The standalone scripts component directly queries OpenRouter metadata to retrieve real-time pricing, throughput, and latency data for endpoint selection.