Skip to main content

Documentation Index

Fetch the complete documentation index at: https://www.truefoundry.com/llms.txt

Use this file to discover all available pages before exploring further.

​
Response Format

The API returns metrics data in JSON format. Aggregation results are returned with keys in camelCase format: {aggregationType}{ColumnName} where the column name is capitalized (e.g., countModelName, sumInputTokens, p99LatencyMs).

​
Distribution Response

{
    "data": [
        {
            "modelName": "gpt-4",
            "countModelName": 150,
            "sumInputTokens": 125000,
            "sumOutputTokens": 45000,
            "p99LatencyMs": 2450.5
        },
        {
            "modelName": "gpt-3.5-turbo",
            "countModelName": 320,
            "sumInputTokens": 89000,
            "sumOutputTokens": 32000,
            "p99LatencyMs": 1820.3
        }
    ]
}

​
Timeseries Response

{
    "data": [
        {
            "timestamp": "2025-01-21T00:00:00.000Z",
            "modelName": "gpt-4",
            "countModelName": 25,
            "sumInputTokens": 15000,
            "p99LatencyMs": 2100.5
        },
        {
            "timestamp": "2025-01-21T01:00:00.000Z",
            "modelName": "gpt-4",
            "countModelName": 30,
            "sumInputTokens": 18500,
            "p99LatencyMs": 2350.2
        }
    ]
}
If the groupBy array is empty, the API returns a summarized overview of all requests within the specified time range.