A real-time intelligence tool for comparing LLM costs, capabilities, and task-specific performance via the OpenRouter API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install 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 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 is a specialized utility designed for developers and AI engineers who need immediate, data-driven insights into the rapidly evolving landscape of Large Language Models. By fetching live data from OpenRouter, this tool provides access to pricing and capability metrics for over 200 models, enabling users to make informed decisions about their AI infrastructure.
Integrating this tool into your workflow via Openclaw Skills allows for seamless auditing of AI stacks. Whether you are looking for the lowest latency model for a chatbot or a high-reasoning model for complex logic, Model Intel provides the technical transparency needed to balance performance and cost effectively.
Model Intel Use Cases
- Comparing model pricing and capabilities side-by-side to minimize operational overhead.
- Identifying the best-performing models for specialized tasks such as programming, logic, or vision-based processing.
- Checking current model availability and maximum context lengths for large document analysis.
- Finding budget-friendly alternatives that meet specific performance or latency requirements.
How Model Intel Works
- The skill connects to the OpenRouter API using your provided credentials to pull the latest model metadata.
- Users input specific queries or commands to filter the model list by name, provider, or task capability.
- The tool performs a comparison or ranking based on real-time pricing (prompt/completion tokens) and architectural features.
- Structured intelligence is delivered through the CLI, allowing for quick integration into development decisions or automated scripts.
Model Intel Setup
To get started with Model Intel, ensure you have Python 3.10+ and an OpenRouter API key.
- Configure your environment variable:
export OPENROUTER_API_KEY='your_api_key_here'
- Execute the script to search or compare models:
# Search for specific models
python3 scripts/model_intel.py search "claude"
# Compare two models
python3 scripts/model_intel.py compare "claude-3-opus" "gpt-4o"
Model Intel Data Schema & Taxonomy
Model Intel structures its output based on real-time API responses, organizing data into the following taxonomy:
| Field | Description |
|---|---|
| Model ID | The unique identifier used for API calls (e.g., anthropic/claude-3-sonnet). |
| Pricing | Detailed breakdown of costs for input and output tokens. |
| Context Window | The maximum number of tokens the model can process in a single request. |
| Capabilities | Specific features such as vision support, function calling, or long-context handling. |
| Task Score | A calculated recommendation for categories like code, reasoning, or speed. |
Model Intel Advanced Features
- Task-specific optimization: Use specialized filters to find the best models for code, vision, or long-context tasks instantly.
- Real-time cost auditing: Monitor the latest pricing shifts across 200+ models to ensure your Openclaw Skills implementations remain cost-effective.
- Side-by-side benchmarking: Compare two different model endpoints to evaluate trade-offs between price and intelligence.
- Automated model discovery: Quickly list top-tier models by provider to stay updated on the latest industry releases.
SKILL.md
Loading
Related Openclaw Skills
Model Intel
A powerful tool for fetching live LLM pricing, capabilities, and performance comparisons directly from OpenRouter.
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.
Moralis
A comprehensive Web3 data integration for agents to query blockchain balances, token prices, and NFT metadata across multiple networks.
Mux Video Management
A robust Python CLI tool for programmatically managing Mux video assets, live streams, and engagement metrics.
Featured*
