A dynamic utility for querying real-time OpenRouter data to find, compare, and price Large Language Models on the fly.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agxntsix-model-intel
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install agxntsix-model-intel using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Model Intel?
Model Intel provides developers and AI agents with up-to-the-minute intelligence on Large Language Models via the OpenRouter API. Unlike static documentation that becomes outdated, this skill offers live data on pricing, context windows, and specific model capabilities. It serves as a critical infrastructure layer for users of Openclaw Skills who need to dynamically select the most cost-effective or highest-performing model for specialized computational tasks.
By integrating this skill into your environment, you gain the ability to search for models by provider, compare parameters side-by-side, and identify the best model for specific niches like vision, coding, or high-speed reasoning. It ensures that your automated workflows are always utilizing the most current data available in the rapidly evolving AI landscape.
Model Intel Use Cases
- Identifying the most affordable LLM for high-volume background data processing.
- Comparing Claude and GPT models side-by-side to determine the best fit for specific coding tasks.
- Finding the best vision-capable or long-context models currently available on the market.
- Automating model selection within agentic workflows based on real-time pricing and availability.
How Model Intel Works
- The script authenticates with OpenRouter using a secure API key to fetch the latest global model metadata.
- The user or agent executes CLI commands to filter, search, or compare specific model specifications.
- The tool processes the raw JSON data from the provider to extract pricing (input/output) and capability tags.
- Based on input parameters like 'fast', 'code', or 'cheap', the skill ranks available models and returns the optimal recommendation.
Model Intel Setup
To integrate this tool into your Openclaw Skills setup, follow these steps:
# Set your OpenRouter API Key environment variable
export OPENROUTER_API_KEY='your_api_key_here'
# Ensure Python 3.10+ and requirements are installed
pip install requests
# Run a test command to list available models
python3 scripts/model_intel.py list
Model Intel Data Schema & Taxonomy
The skill organizes model intelligence into a structured format for easy analysis:
| Attribute | Description |
|---|---|
| Model ID | The unique identifier for the model (e.g., anthropic/claude-3-opus). |
| Pricing | Live cost per million tokens for both prompt and completion stages. |
| Context Window | The maximum token capacity supported by the model architecture. |
| Use Case Tags | Specialized markers such as 'vision', 'reasoning', or 'coding'. |
Model Intel Advanced Features
- Real-time side-by-side comparison engine for two specific model variants.
- Heuristic-based recommendations for specialized workloads like fast responses or low-cost reasoning.
- Seamless integration into the broader Openclaw Skills ecosystem for multi-agent coordination.
- Direct access to live provider data to bypass stale local training knowledge.
SKILL.md
Loading
Related Openclaw Skills
Deep Search
Deep Search is a sophisticated search routing engine for Openclaw Skills that leverages Perplexity AI models to provide tiered web research capabilities.
Agent Memory
A sophisticated intelligence layer providing vector search, knowledge graphs, and structured data storage for AI agents.
OpenClaw Architect
A comprehensive management and optimization tool for designing, debugging, and maintaining high-performance OpenClaw deployments.
GitHub Intelligence
A specialized tool for AI agents to analyze GitHub repositories, generate architecture diagrams, and convert codebases into AI-readable markdown documents.
Research Logger
An automated AI research pipeline that logs search results from Perplexity into a structured SQLite database with full Langfuse observability.
Skill Auditor
A mandatory security auditing and quarantine system designed to evaluate third-party Openclaw Skills for safety and compliance.
Featured*
