A comprehensive auditing tool that compares your current LLM stack against live OpenRouter pricing to find cheaper and more powerful model alternatives.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install model-audit-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-audit-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 Audit?
Model Audit is a specialized utility designed to keep your AI infrastructure on the cutting edge while minimizing operational overhead. By fetching live pricing and performance benchmarks from OpenRouter, it provides a deep-dive analysis of your configured models. It is built to serve developers using Openclaw Skills who need to maintain a balance between high-performance reasoning and cost-effective execution.
The tool categorizes models into specific niches such as reasoning, coding, speed, and vision. This classification allows users to see exactly where their stack is over-provisioned or where a newer, cheaper model could provide better results. It transforms complex pricing data into actionable insights for maintaining a lean and efficient AI stack.
Model Audit Use Cases
- Periodic auditing of AI infrastructure to reduce monthly token spend.
- Benchmarking newly released models against your existing production stack.
- Validating that your agent has the necessary model coverage for specialized tasks like vision or coding.
- Generating structured JSON reports for financial oversight and AI resource planning.
How Model Audit Works
- The script connects to the OpenRouter API to retrieve current token pricing and model metadata.
- It analyzes your local environment and configuration to identify currently utilized models.
- Models are mapped into functional categories including reasoning, code, fast, cheap, and vision.
- The tool calculates potential savings by comparing your current costs against the best-in-class alternatives.
- A detailed report is generated with specific recommendations for model upgrades or migrations.
Model Audit Setup
To get started, ensure you have your API key configured in your environment. You can then run the audit directly from your terminal:
# Set your API key
export OPENROUTER_API_KEY='your_api_key_here'
# Run the full audit
python3 scripts/model_audit.py
# Compare specific models
python3 scripts/model_audit.py --compare "anthropic/claude-3-sonnet" "openai/gpt-4o"
Model Audit Data Schema & Taxonomy
The model audit tool processes configuration data and outputs analytical summaries. It primarily interacts with the following data points:
| Data Type | Description |
|---|---|
| Source Config | Reads from the openclaw.json file to identify active models. |
| API Data | Live pricing (input/output per 1M tokens) from OpenRouter. |
| Taxonomy | Classification by capability (Reasoning, Code, Fast, Cheap, Vision). |
| Export Format | Standard terminal output or machine-readable JSON via the --json flag. |
Model Audit Advanced Features
- Multi-model comparison mode for side-by-side cost-benefit analysis.
- Automated category coverage check to ensure your agent has access to diverse model types.
- JSON output support for integration into automated DevOps and FinOps workflows.
- Top-tier model filtering to quickly identify the current leaders in price-to-performance within the ecosystem of Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Mercury Banking
A professional-grade Mercury banking integration for AI agents that automates transaction tracking, cash flow analysis, and financial categorization.
Make (Integromat) Automation
A high-performance Python tool for managing Make automation scenarios, executions, connections, and data stores through a zero-dependency API interface.
Mac Mini AI Server for OpenClaw
A comprehensive deployment guide for running Openclaw Skills on a dedicated Mac Mini server for 24/7 AI availability.
Loom
A Python-powered interface to manage Loom video recordings, transcripts, and workspace folders via the official Developer API.
Model Audit
A diagnostic tool within the Openclaw Skills ecosystem designed to audit LLM stacks against live OpenRouter pricing and performance benchmarks.
Model Council
A multi-model consensus engine that queries several LLMs simultaneously and uses a judge model to synthesize the best possible answer.
Featured*
