---
title: "Get Model Metrics"
method: POST
path: "/analytics/model-metrics"
tags: ["analytics"]
---

# Get Model Metrics

`POST /analytics/model-metrics`

Return per-model metrics for the last 24 hours.

Counts, error counts, average latency, and last-inference timestamp are
all scoped to the last 24 hours. ``latest_evaluation`` is all-time.

Args:
    request: Batch of model ids to look up.
    auth: Authentication result carrying the user id and team scope.

Returns:
    ``ModelMetricsResponse`` with an entry for each requested id.

## Request body

- ModelMetricsRequest — Batch request body for model metrics lookup.
  - `model_ids` string[], required — Model identifiers to compute metrics for. Accepts training-job UUIDs and base catalog ids.
  - `since` string, date-time, nullable — Inclusive start of the rollup window (UTC). Defaults to 24 hours ago, preserving the legacy last-24h behaviour. Drives the page-level date picker on the models / routers surfaces.
  - `until` string, date-time, nullable — Exclusive end of the rollup window (UTC). Defaults to now.

## Response `200`

Successful Response

- ModelMetricsResponse — Batch response mapping input model id -> ModelMetrics. Every requested id is present in ``metrics``; ids with no matching inference rows in the last 24 hours map to a zero-filled ``ModelMetrics``.
  - `metrics` object

## Other responses

- `422` — Validation Error
- `503` — Model metrics dependency is temporarily unavailable.

---

[API](https://skmtc.net/pioneer/apis/brain-api.md) · [All operations](https://skmtc.net/pioneer/apis/brain-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/pioneer/brain-api/revisions/31dfe831e079/schema)