How do I install the Openrouter Analyzer skill?

Run npx skillmds@latest add notabanker/openrouter-analyzer in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Openrouter Analyzer safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Openrouter Analyzer?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Openrouter Analyzer free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Openrouter Analyzer?

notabanker (@notabanker) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Openrouter Analyzer by notabanker — Agent Skill

Name: Openrouter Analyzer
Author: notabanker

Openrouter Analyzer

Analyze OpenRouter API usage CSV exports to calculate costs, token usage, and efficiency metrics by hour, day, model, and provider. Use when the user attaches a CSV file from OpenRouter, mentions analyzing token usage, cost analysis, or OpenRouter usage data. Automatically detects OpenRouter CSV format and generates hourly breakdowns, model usage stats, and provider cost breakdowns.

notabanker a9c1e7e 2 files · 14.1 KB Updated Sep 17, 2026

File contents

OpenRouter Usage Analyzer

Analyzes OpenRouter API usage exports to provide cost and token insights.

When to Use

User attaches a CSV file from OpenRouter dashboard
User asks to analyze token usage or costs
User mentions OpenRouter usage data
User wants hourly/daily cost breakdowns

How to Use

When triggered by CSV attachment or usage analysis request:

Save the attached CSV to a temp location if needed
Run the analyzer script: python3 scripts/analyze.py <csv_path> --model --provider
Present the results in a clean, formatted way highlighting:
- Total spend and cost per request
- Peak usage hours
- Model breakdown (Kimi, Mimo, etc.)
- Provider costs (Moonshot, Chutes, Novita, etc.)
- Cost efficiency metrics

Output Format

Present results in sections:

💰 Cost Efficiency (total spend, per-request cost, avg latency)
📊 Hourly Breakdown (cost per hour, requests, tokens)
📅 Daily Summary (if multi-day)
🤖 Model Breakdown (which models cost what)
🏢 Provider Breakdown (which providers used)

Script Usage

# Basic analysis
python3 scripts/analyze.py <csv_file>

# With all breakdowns
python3 scripts/analyze.py <csv_file> --model --provider

# Export to CSV
python3 scripts/analyze.py <csv_file> --export output.csv

The script has no dependencies - uses only Python standard library.

Frequently asked questions