A powerful tool for fetching live LLM pricing, capabilities, and performance comparisons directly from OpenRouter.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install model-intel-pro
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 model-intel-pro 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 is a specialized extension designed for Openclaw Skills that provides developers and AI agents with real-time intelligence on Large Language Models. By interfacing with the OpenRouter API, it ensures that users always have access to the most current data regarding model availability, context windows, and pricing structures.
Whether you are building a cost-sensitive application or need the highest-performing reasoning model, this skill automates the discovery process. It allows your agent to make data-driven decisions about which model to use for specific tasks, ensuring performance is never compromised by outdated information.
Model Intel Use Cases
- Identify the most cost-effective LLM for high-volume tasks using Openclaw Skills.
- Compare specific models side-by-side to evaluate context lengths and feature sets.
- Locate the best performing models for niche tasks like coding, vision, or complex reasoning.
- Monitor live pricing updates to manage API budgets effectively.
How Model Intel Works
- The skill initializes by verifying the OpenRouter API key provided in the environment variables.
- Users or agents trigger specific commands such as list, search, or compare via the CLI.
- The tool fetches the latest model registry data directly from the OpenRouter API endpoint.
- It filters and ranks models based on the specified criteria such as latency, cost, or task suitability.
- Results are returned in a structured format for easy interpretation by both humans and AI agents.
Model Intel Setup
To integrate Model Intel into your collection of Openclaw Skills, follow these steps:
- Ensure Python 3 is installed on your system.
- Export your OpenRouter API key as an environment variable:
export OPENROUTER_API_KEY='your_api_key_here'
- Execute the script using the Python CLI:
python3 scripts/model_intel.py list
Model Intel Data Schema & Taxonomy
Model Intel processes and displays data across several key metrics to help you manage Openclaw Skills resources efficiently:
| Metric | Description |
|---|---|
| Model ID | The unique identifier for the LLM on OpenRouter |
| Pricing | Input and output costs per million tokens |
| Context Length | Maximum token capacity for the model |
| Capability Tags | Labels such as vision, coding, or reasoning |
| Provider | The underlying host for the model API |
Model Intel Advanced Features
- Automatic recommendation engine for selecting models based on 'fast', 'cheap', or 'code' presets.
- Deep-search functionality to find specific model variants across all providers.
- Dynamic pricing comparison between top-tier models like GPT-4o and Claude 3.5 Sonnet.
- Seamless integration with Openclaw Skills workflows to programmatically select the best LLM at runtime.
SKILL.md
Loading
Related Openclaw Skills
Model Council
A multi-model consensus system that queries multiple LLMs simultaneously and uses a high-tier judge model to synthesize the best possible answer.
Model Council
A multi-model consensus engine that queries several LLMs simultaneously and uses a judge model to synthesize the best possible answer.
Model Audit
A diagnostic tool within the Openclaw Skills ecosystem designed to audit LLM stacks against live OpenRouter pricing and performance benchmarks.
Model Audit
A comprehensive auditing tool that compares your current LLM stack against live OpenRouter pricing to find cheaper and more powerful model alternatives.
Model Intel
A real-time intelligence tool for comparing LLM costs, capabilities, and task-specific performance via the OpenRouter API.
Moralis
A comprehensive Web3 data integration for agents to query blockchain balances, token prices, and NFT metadata across multiple networks.
Featured*
