A CLI-based catalog analyzer that pulls live metadata for OpenRouter models to filter, sort, and compare prices across multiple providers.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openrouter-models
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 openrouter-models 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 OpenRouter Models Analyzer?
The OpenRouter Models Analyzer is a command-line tool designed to query, cache, and dissect the full suite of LLMs available on OpenRouter. By fetching real-time model definitions from OpenRouter's public API, this analyzer normalizes complex pricing structures—covering up to eight distinct dimensions including prompt, completion, cache read/write, and reasoning—into a standard dollar-per-million-tokens rate.
This utility operates completely offline once the initial cache is generated. Developers can easily query models by provider family, identify free alternatives, isolate vision-capable models, and evaluate context-length options. It is an indispensable utility for engineering teams looking to optimize their LLM API spend using Openclaw Skills.
OpenRouter Models Analyzer Use Cases
- Optimizing API Cost: Find the cheapest LLM that supports specific functionalities like image inputs or prompt caching.
- Vendor & Provider Analysis: Filter and compare models from specific creators like Anthropic, OpenAI, DeepSeek, or Google.
- Feature Discovery: Locate free-tier models or models supporting advanced input/output modalities (vision, audio, or video).
- Programmatic Integration: Output model pricing structures as structured JSON for dynamic configuration in production environments.
How OpenRouter Models Analyzer Works
- Fetch Live Catalog: Run the ingestion script to hit the public OpenRouter API and download the latest specifications, storing them locally.
- Normalize Pricing: The tool processes raw metadata, standardizing input, output, cache, and search prices into a readable format of dollars per 1 million tokens or calls.
- Query Offline: Execute the analysis script with customizable search flags, sorting options, and limits without needing active network connections.
- Format Output: Generate highly aligned terminal tables, structural JSON, or coverage statistics based on your command-line arguments.
OpenRouter Models Analyzer Setup
Ensure you have Python 3 installed. This tool runs directly via the CLI and does not require an OpenRouter API key for metadata extraction.
# 1. Fetch the latest live catalog (no API key needed)
python3 scripts/fetch_models.py
# -> writes models_raw.json next to the script
# 2. Analyze the cached data with filters (e.g., Anthropic models)
python3 scripts/analyze.py --family anthropic/
# 3. Analyze with advanced criteria
python3 scripts/analyze.py --has-image --min-ctx 1000000 --sort prompt --limit 20
OpenRouter Models Analyzer Data Schema & Taxonomy
The retrieved catalog caches locally as models_raw.json. The normalized pricing model structure extracts the following metadata properties:
| Property | Type | Description |
|---|---|---|
id |
String | Unique identifier of the model (e.g., anthropic/claude-3-opus) |
name |
String | Display name of the model |
context_length |
Integer | Maximum context window supported by the model |
input_modalities |
Array | Supported inputs (e.g., text, image, audio, video) |
output_modalities |
Array | Supported outputs (e.g., text, image) |
prompt |
Float | Cost per 1M prompt tokens (USD) |
completion |
Float | Cost per 1M completion tokens (USD) |
input_cache_read |
Float | Cost per 1M tokens read from prompt cache (USD) |
input_cache_write |
Float | Cost per 1M tokens written to prompt cache (USD) |
web_search |
Float | Cost per 1M web search invocations (USD) |
internal_reasoning |
Float | Cost per 1M reasoning tokens (USD) |
Note: A price of -1 indicates dynamic or variable pricing typical of router endpoints.
OpenRouter Models Analyzer Advanced Features
- Prompt Cache Detection: Easily filter for modern models that offer cost savings via prompt caching APIs using the
--has-cacheflag. - Reasoning Price Analysis: Evaluate cost implications for specialized reasoning models (like o1 or DeepSeek-R1) with the
--has-reasoning-priceflag. - Comprehensive Metadata Statistics: Run command-line reports using
--statsto get a high-level breakdown of modality coverage, average rates, and pricing support. - JSON Output Integration: Streamline multi-agent workflows by passing
--jsonto pipeline structured model constraints directly into your automation pipelines utilizing Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Multimodal Image Understanding Skill
A bridge skill enabling text-only AI models to analyze, OCR, and extract details from images via OpenAI or Anthropic protocols.
Doubt-Driven Development
Doubt-Driven Development is an advanced engineering workflow that introduces isolated adversarial sub-agents to review non-trivial decisions before execution, preventing context pollution and overconfidence errors.
Baoqingtian MVP Verdict Engine
An AI-powered product validation engine for evaluating MVP ideas and creator tools with structured evidence ratings, interactive verdict cards, and 7-day execution roadmaps.
Crypto Monitor
An automated cryptocurrency monitoring and alert generation tool for real-time market tracking without manual screen-watching.
Database Schema Designer
A production-grade AI agent skill designed to bridge the gap between business requirements and optimized, scalable database schemas.
Agent Accounting
An AI-powered automated bookkeeping and tax filing agent designed for accounting firms to streamline OCR receipt processing, voucher creation, and financial reporting.
crypto-monitor
An automated cryptocurrency monitoring tool that provides live price tracking, intelligent alerts, and comprehensive market reports for digital assets.
Featured*
