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.

​
Timeseries Queries

Get hourly request counts:
response = requests.post(
    "https://{your_control_plane_url}/api/svc/v1/llm-gateway/metrics/query",
    headers={
        "Authorization": "Bearer <your_api_key>",
        "Content-Type": "application/json"
    },
    json={
        "startTs": "2025-01-21T00:00:00.000Z",
        "endTs": "2025-01-22T00:00:00.000Z",
        "datasource": "modelMetrics",
        "type": "timeseries",
        "aggregations": [
            {"type": "count", "column": "modelName"}
        ],
        "filters": [
            {
                "fieldName": "virtualModelName",
                "operator": "IS_NULL",
                "value": true
            }
        ],
        "intervalInSeconds": 3600
    }
)
Get fine-grained metrics with 5-minute intervals:
response = requests.post(
    "https://{your_control_plane_url}/api/svc/v1/llm-gateway/metrics/query",
    headers={
        "Authorization": "Bearer <your_api_key>",
        "Content-Type": "application/json"
    },
    json={
        "startTs": "2025-01-21T00:00:00.000Z",
        "endTs": "2025-01-21T06:00:00.000Z",
        "datasource": "modelMetrics",
        "type": "timeseries",
        "aggregations": [
            {"type": "count", "column": "modelName"}
        ],
        "filters": [
            {
                "fieldName": "virtualModelName",
                "operator": "IS_NULL",
                "value": true
            }
        ],
        "intervalInSeconds": 300
    }
)
Get hourly counts grouped by model:
response = requests.post(
    "https://{your_control_plane_url}/api/svc/v1/llm-gateway/metrics/query",
    headers={
        "Authorization": "Bearer <your_api_key>",
        "Content-Type": "application/json"
    },
    json={
        "startTs": "2025-01-21T00:00:00.000Z",
        "endTs": "2025-01-22T00:00:00.000Z",
        "datasource": "modelMetrics",
        "type": "timeseries",
        "aggregations": [
            {"type": "count", "column": "modelName"}
        ],
        "filters": [
            {
                "fieldName": "virtualModelName",
                "operator": "IS_NULL",
                "value": true
            }
        ],
        "groupBy": ["modelName"],
        "intervalInSeconds": 3600
    }
)
Get hourly counts grouped by team:
response = requests.post(
    "https://{your_control_plane_url}/api/svc/v1/llm-gateway/metrics/query",
    headers={
        "Authorization": "Bearer <your_api_key>",
        "Content-Type": "application/json"
    },
    json={
        "startTs": "2025-01-21T00:00:00.000Z",
        "endTs": "2025-01-22T00:00:00.000Z",
        "datasource": "modelMetrics",
        "type": "timeseries",
        "aggregations": [
            {"type": "count", "column": "team"}
        ],
        "filters": [
            {
                "fieldName": "virtualModelName",
                "operator": "IS_NULL",
                "value": true
            }
        ],
        "groupBy": ["team"],
        "intervalInSeconds": 3600
    }
)
Apply filters to timeseries data:
response = requests.post(
    "https://{your_control_plane_url}/api/svc/v1/llm-gateway/metrics/query",
    headers={
        "Authorization": "Bearer <your_api_key>",
        "Content-Type": "application/json"
    },
    json={
        "startTs": "2025-01-21T00:00:00.000Z",
        "endTs": "2025-01-22T00:00:00.000Z",
        "datasource": "modelMetrics",
        "type": "timeseries",
        "aggregations": [
            {"type": "count", "column": "modelName"}
        ],
        "filters": [
            {
                "fieldName": "virtualModelName",
                "operator": "IS_NULL",
                "value": true
            },
            {
                "fieldName": "modelName",
                "operator": "IN",
                "value": ["gpt-4", "gpt-3.5-turbo"]
            }
        ],
        "groupBy": ["modelName"],
        "intervalInSeconds": 3600
    }
)
Filter timeseries by latency threshold:
response = requests.post(
    "https://{your_control_plane_url}/api/svc/v1/llm-gateway/metrics/query",
    headers={
        "Authorization": "Bearer <your_api_key>",
        "Content-Type": "application/json"
    },
    json={
        "startTs": "2025-01-21T00:00:00.000Z",
        "endTs": "2025-01-22T00:00:00.000Z",
        "datasource": "modelMetrics",
        "type": "timeseries",
        "aggregations": [
            {"type": "count", "column": "modelName"}
        ],
        "filters": [
            {
                "fieldName": "virtualModelName",
                "operator": "IS_NULL",
                "value": true
            },
            {
                "fieldName": "latencyMs",
                "operator": "GREATER_THAN",
                "value": 500
            }
        ],
        "groupBy": ["modelName"],
        "intervalInSeconds": 3600
    }
)
Filter timeseries by team:
response = requests.post(
    "https://{your_control_plane_url}/api/svc/v1/llm-gateway/metrics/query",
    headers={
        "Authorization": "Bearer <your_api_key>",
        "Content-Type": "application/json"
    },
    json={
        "startTs": "2025-01-21T00:00:00.000Z",
        "endTs": "2025-01-22T00:00:00.000Z",
        "datasource": "modelMetrics",
        "type": "timeseries",
        "aggregations": [
            {"type": "count", "column": "modelName"}
        ],
        "filters": [
            {
                "fieldName": "virtualModelName",
                "operator": "IS_NULL",
                "value": true
            },
            {
                "fieldName": "team",
                "operator": "ARRAY_HAS_ANY",
                "value": ["team-alpha", "team-beta"]
            }
        ],
        "groupBy": ["team"],
        "intervalInSeconds": 3600
    }
)
Group timeseries by metadata:
response = requests.post(
    "https://{your_control_plane_url}/api/svc/v1/llm-gateway/metrics/query",
    headers={
        "Authorization": "Bearer <your_api_key>",
        "Content-Type": "application/json"
    },
    json={
        "startTs": "2025-01-21T00:00:00.000Z",
        "endTs": "2025-01-22T00:00:00.000Z",
        "datasource": "modelMetrics",
        "type": "timeseries",
        "aggregations": [
            {"type": "count", "column": "modelName"}
        ],
        "filters": [
            {
                "fieldName": "virtualModelName",
                "operator": "IS_NULL",
                "value": true
            }
        ],
        "groupBy": ["metadata.environment"],
        "intervalInSeconds": 3600
    }
)
Get daily data for a week:
response = requests.post(
    "https://{your_control_plane_url}/api/svc/v1/llm-gateway/metrics/query",
    headers={
        "Authorization": "Bearer <your_api_key>",
        "Content-Type": "application/json"
    },
    json={
        "startTs": "2025-01-14T00:00:00.000Z",
        "endTs": "2025-01-21T00:00:00.000Z",
        "datasource": "modelMetrics",
        "type": "timeseries",
        "aggregations": [
            {"type": "count", "column": "modelName"}
        ],
        "filters": [
            {
                "fieldName": "virtualModelName",
                "operator": "IS_NULL",
                "value": true
            }
        ],
        "intervalInSeconds": 86400
    }
)
Combine filters, groupBy, and metadata:
response = requests.post(
    "https://{your_control_plane_url}/api/svc/v1/llm-gateway/metrics/query",
    headers={
        "Authorization": "Bearer <your_api_key>",
        "Content-Type": "application/json"
    },
    json={
        "startTs": "2025-01-21T00:00:00.000Z",
        "endTs": "2025-01-22T00:00:00.000Z",
        "datasource": "modelMetrics",
        "type": "timeseries",
        "aggregations": [
            {"type": "count", "column": "modelName"}
        ],
        "filters": [
            {
                "fieldName": "virtualModelName",
                "operator": "IS_NULL",
                "value": true
            },
            {
                "fieldName": "modelName",
                "operator": "IN",
                "value": ["gpt-4", "gpt-3.5-turbo"]
            },
            {
                "metadataKey": "environment",
                "operator": "IN",
                "value": ["production"]
            }
        ],
        "groupBy": ["modelName"],
        "intervalInSeconds": 3600
    }
)