OpenRouter Models
0This skill allows you to discover, search, and compare over 300 AI models available on OpenRouter. It provides live data including pricing, context lengths, and performance metrics for different AI model providers.
16900Updated 2mo ago
AI Models
Quick InstallView Source
$ npx skills add https://github.com/openrouterteam/skills --skill openrouter-modelsOverview
About This Skill
The OpenRouter Models skill enables developers to programmatically query available models, compare pricing across providers, check context window lengths, and resolve model names with fuzzy matching. It provides real-time access to OpenRouter's catalog of 600+ AI models, helping teams make informed decisions about which models best fit their use case and budget. This skill integrates seamlessly with Claude Code, Cursor, and other Agent Skills-compatible platforms, giving developers instant visibility into model capabilities, costs, and performance characteristics without leaving their development environment.
How to Use
Install using npx and query models for various performance data.
Use Cases
Compare AI model features and pricing
Retrieve model performance metrics
Search for specific AI models based on user needs
Tags
Setup & Installation
Quick Install
Terminal
$ npx skills add https://github.com/openrouterteam/skills --skill openrouter-modelsAlternative Install (Git Clone)
git clone https://github.com/openrouterteam/skillsRequirements
- Claude Code or compatible AI agent
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
List the top 5 AI models on OpenRouter for [TASK: e.g., 'creative writing', 'code generation', 'data analysis'] based on [CRITERIA: e.g., 'cost-effectiveness', 'context length', 'performance score']. Provide their pricing per 1M tokens, max context length, and key strengths. Focus on models from [PROVIDER PREFERENCE: e.g., 'Anthropic', 'Mistral', 'Meta', 'Google', or 'any'].
Example Output
### Top 5 AI Models for Code Generation on OpenRouter Here are the best-performing models for code generation, ranked by **performance-to-cost ratio** (as of October 2024). | **Model** | **Provider** | **Price (per 1M tokens)** | **Max Context** | **Key Strengths** | |-------------------------|---------------|---------------------------|-----------------|--------------------------------------------| | **codellama-70b-instruct** | Meta | $0.80 (input) / $2.00 (output) | 100K tokens | Excellent for Python, Java, and C++; strong reasoning. | | **deepseek-coder-33b-instruct** | DeepSeek | $0.40 (input) / $1.60 (output) | 16K tokens | Specialized in code completion and debugging. Fast inference. | | **mistral-large-2407** | Mistral AI | $2.00 (input) / $6.00 (output) | 128K tokens | High accuracy in multi-language code generation. | | **claude-3-5-sonnet** | Anthropic | $3.00 (input) / $15.00 (output) | 200K tokens | Best for complex logic and long codebases. | | **gpt-4o-mini** | OpenAI | $0.40 (input) / $1.20 (output) | 128K tokens | Balanced cost and performance for general coding tasks. | **Recommendation:** If you're working on **large codebases**, `claude-3-5-sonnet` is ideal despite its higher cost. For **budget-friendly** solutions, `deepseek-coder-33b-instruct` or `gpt-4o-mini` are strong choices. Would you like a comparison for a specific programming language or use case?
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan