---
title: "Get pod CPU metrics"
method: GET
path: "/v2/metrics/cpu/pods/{pod_id}"
tags: ["Metrics"]
---

# Get pod CPU metrics

`GET /v2/metrics/cpu/pods/{pod_id}`

## Request

- The document declares no server URL.
- Auth: none required
- TypeScript: <https://skmtc.dev/yottalabs/apis/docs-yottalabs-ai/docs/v2/metrics/cpu/pods/:pod_id/get.ts> (a function with typed inputs; its response is checked against the schema)

Returns CPU usage ratio time series.
Unit: ratio, where 1.0 means 100% of requested CPU cores.

## Path parameters

- `pod_id` integer, required

## Query parameters

- `start` integer
- `end` integer
- `step` 'auto' | '30s' | '5m' | '15m' | '1h' | '4h' | '1d'

## Response `200`

OK

- object: Standard API envelope
  - `code` integer
  - `message` string
  - `data` object: Metric result for utilization metrics (CPU, GPU) without capacity information
    - `metric_name` string, required: Name of the metric (e.g. cpu_usage, gpu_utilization)
    - `series` TimeSeriesNoCapacity[], required: Array of time series data without capacity metrics
      - `labels` object, required: Key-value label set identifying this series (e.g. pod_id, gpu_show_index)
      - `data_points` DataPoint[], required: Array of timestamped metric values
        - `timestamp` integer: Unix timestamp in milliseconds
        - `value` number, double

## Other responses

- `400`: Bad Request
- `401`: Unauthorized — missing or invalid x-api-key
- `403`: Forbidden — valid key but insufficient permissions
- `404`: Not Found — pod does not exist
- `500`: Internal Server Error
- `503`: Service Unavailable

---

[API](https://skmtc.dev/yottalabs/apis/docs-yottalabs-ai.md) - [All operations](https://skmtc.dev/yottalabs/apis/docs-yottalabs-ai/llms.txt) - [OpenAPI document](https://skmtc.dev/yottalabs/apis/docs-yottalabs-ai/revisions/998cc08df103?raw)