Get model performance metrics
get_model_performance_metricsRetrieve token, latency, and call-count metrics for AI models, optionally filtered by model and timeframe, to analyze usage and performance.
Instructions
Read token, latency and call counts from Studio insightsLanguageModelUsage. Use get_insights_usage as the same data under a shorter name. Use get_conversation_patterns for chat shape. Read-only. Returns JSON totals and per-model rows.
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": "get_model_performance_metrics"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model_id | No | Optional model id to filter. Omit for all models. | |
| timeframe | No | Window such as 7d, 30d or all. Default 7d. | 7d |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |