Model Intel
Live LLM model intelligence and pricing from OpenRouter
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/aiwithabidi/agxntsix-model-intelWhat This Skill Does
The Model Intel skill for OpenClaw acts as a dynamic, real-time interface for the OpenRouter model ecosystem. Unlike static documentation or training data that becomes obsolete as soon as a new model is released, Model Intel queries live APIs to retrieve current performance metrics, pricing structures, and capability snapshots. Whether you are an AI developer optimizing for cost-efficiency or a power user searching for the best reasoning model for a complex task, this tool provides the analytical data required to make informed decisions.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/aiwithabidi/agxntsix-model-intel
Ensure you have the requests library installed (pip install requests) and that your OPENROUTER_API_KEY is exported as an environment variable in your shell configuration or current session. This ensures that the skill can authenticate against the OpenRouter service seamlessly.
Use Cases
- Budget Optimization: Developers can audit the cost per token of different models to minimize infrastructure spend while maintaining performance thresholds.
- Task-Specific Selection: Quickly determine which model currently excels in specific domains, such as creative writing, coding benchmarks, or multi-modal vision tasks.
- Vendor Agnostic Analysis: Compare the performance profiles of top-tier models from providers like Anthropic, OpenAI, Google, and Meta side-by-side without needing to manually cross-reference various platform dashboards.
Example Prompts
- "OpenClaw, use Model Intel to compare the current pricing of Claude 3.5 Sonnet against GPT-4o for a high-volume coding project."
- "I need a fast model for real-time customer support interactions; can you use the model intel skill to suggest the top 3 cheapest options?"
- "Search for all available 'reasoning' models currently supported by OpenRouter and give me a brief summary of their cost structure."
Tips & Limitations
Tips: Always check the 'best' category filter regularly, as model performance rankings fluctuate following community feedback and new releases. For production systems, use the pricing command to generate a baseline cost estimate before scaling your deployment.
Limitations: This skill requires an active internet connection to function as it fetches data from external APIs. Ensure your OpenRouter API key remains active and has sufficient credits to prevent access interruptions. Note that while pricing and model availability are updated in real-time, qualitative rankings for 'best' performance may vary based on specific prompt engineering nuances.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-aiwithabidi-agxntsix-model-intel": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api
Related Skills
freshsales
Freshsales CRM integration — manage contacts, leads, deals, accounts, tasks, and sales sequences via the Freshsales API. Track deal pipelines, automate lead assignments, log activities, and generate sales reports. Built for AI agents — Python stdlib only, no dependencies. Use for sales CRM, contact management, deal tracking, pipeline reporting, and sales automation.
gemini-video-analyzer
Native video analysis using Google Gemini API. Upload and analyze video files — describe scenes, extract text/UI, answer questions about content, transcribe speech, identify objects and actions. Use when: (1) User sends a video file and wants it analyzed, (2) Video summarization or description needed, (3) Extracting text, UI elements, or information from screen recordings, (4) Answering questions about video content, (5) Comparing multiple videos, (6) Analyzing tutorials, demos, or walkthroughs.
agent-memory
Full AI agent memory stack — Mem0 unified memory engine with vector search (Qdrant) and knowledge graph (Neo4j), plus SQLite for structured data. Complete setup script and tools. Give your OpenClaw agent a real brain with semantic recall, entity relationships, and structured storage.
neon
Neon serverless Postgres — manage projects, branches, databases, roles, endpoints, and compute via the Neon API. Create database branches for development, manage connection endpoints, scale compute, and monitor usage. Built for AI agents — Python stdlib only, zero dependencies. Use for serverless Postgres, database branching, database management, development workflows, and cloud database automation.
onepassword
1Password Connect — vaults, items, secrets management for server-side applications.