tokmeter_leaderboard
Rank AI models or providers by cost, cost efficiency, tokens, cache hit rate, reasoning share, output volume, or records to compare spend and value within a chosen time scope.
Instructions
Rank the top N models or providers (default 10) in a scope by one metric: total cost, cost per 1M tokens (cost_efficiency), total tokens, cache hit rate (cache_rate), reasoning share (reasoning_rate), output tokens, or record count. Returns the entries in rank order with their metrics. Use it to answer "which model costs most / gives the best value"; for every metric of every model at once, use tokmeter_models.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "tokmeter_leaderboard"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Top N to show (default: 10) | |
| scope | No | Time scope: today, week (last 7d), month (calendar month), or all (default) | |
| entity | No | Rank models or providers (default: models) | |
| project | No | Filter by project name/path substring | |
| rank_by | No | Ranking metric (default: cost) |