Openrouter usage

Skill tdimino/claude-code-minoan/skills/core-development/openrouter-usage

Query OpenRouter API costs, credits, and usage breakdown by model, provider, and date for the last 30 days. Triggers on API spending, check costs, openrouter usage, how much have I spent.From its SKILL.md

Install

npx -y skills add tdimino/claude-code-minoan --skill openrouter-usage

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

reads credentialsReads from 2 credential sources: `OPENROUTER_API_KEY` and 1 more.
runs commandsInstructs the agent to run 5 commands, including `python3 ~/.claude/skills/openrouter-usage/scripts/openrouter_usage.py` and 4 more.
fetches URLsInstructs the agent to fetch 2 URLs, including GET /api/v1/credits and 1 more.

SKILL.md

2.1 KB, 475 tokens by cl100k_base, as published. Nobody here has run it

OpenRouter Usage

Query OpenRouter API costs and generate usage reports via the command line.

When to Use

Checking OpenRouter spend over the last 30 days
Breaking down costs by model, provider, or date
Exporting usage data as CSV or JSON for accounting
Auditing which models and API keys consume the most credits

Prerequisites

OPENROUTER_API_KEY environment variable (or in a project .env file)
The key must be a Management key — create one at https://openrouter.ai/settings/management-keys
Regular provisioning keys return 401/403 on analytics endpoints

Usage

# Full 30-day summary with credits balance
python3 ~/.claude/skills/openrouter-usage/scripts/openrouter_usage.py

# Filter to a single date
python3 ~/.claude/skills/openrouter-usage/scripts/openrouter_usage.py --date 2026-02-01

# Export as CSV (for spreadsheets)
python3 ~/.claude/skills/openrouter-usage/scripts/openrouter_usage.py --csv

# Raw JSON output (for piping to jq)
python3 ~/.claude/skills/openrouter-usage/scripts/openrouter_usage.py --json

# Skip credits lookup (activity only)
python3 ~/.claude/skills/openrouter-usage/scripts/openrouter_usage.py --no-credits

Output

The default report includes:

Credits balance: total purchased, used, remaining
Spend by model: per-model cost with token counts (prompt, completion, reasoning)
Spend by provider: aggregated by provider (OpenAI, Anthropic, Google, etc.)
Spend by date: daily spend with visual bar chart

API Endpoints

Both endpoints are read-only GETs authenticated via Bearer token:

Endpoint	Purpose
`GET /api/v1/credits`	Total credits purchased and used
`GET /api/v1/activity`	Last 30 days of usage grouped by model/endpoint/provider

The activity endpoint returns per-row: date, model, provider_name, usage, byok_usage_inference, requests, prompt_tokens, completion_tokens, reasoning_tokens.

What ships with it: 2 files

10.9 KB alongside SKILL.md, 1 of them executable

scripts/

openrouter_usage.pyruns8.9 KB

README.md1.9 KB