---
title: "Aggregate inference metrics (tokens, latency, TPS, crude cost)"
method: GET
path: "/api/deployed-models/{id}/metrics/"
tags: ["deployed-models"]
---

# Aggregate inference metrics (tokens, latency, TPS, crude cost)

`GET /api/deployed-models/{id}/metrics/`

## Request

- Base URL: `https://api.overmindlab.ai`
- URL: `https://api.overmindlab.ai/api/deployed-models/{id}/metrics/`
- Auth: one of:
  - HTTP bearer
  - API key in header `X-Api-Key`
  - API key in cookie `sessionid`
  - API key in header `X-Api-Key`
  - HTTP bearer

## Path parameters

- `id` string, uuid, required

## Query parameters

- `period` '1h' | '24h' | '7d' | '30d' | 'all'
- `source` 'all' | 'application'

## Response `200`

- InferenceMetrics: Aggregate usage/latency/cost for a deployed model (from InferenceCall).
  - `dedicated_usage` DedicatedUsage, required
    - `credits` number, double, nullable, required
    - `gpu_hours` number, double, nullable, required
    - `points` DedicatedUsagePoint[], required
      - `bucket` string, date-time, required
      - `credits` number, double, required
    - `breakdown` DedicatedUsageBreakdown[], required
      - `gpu_type` string, nullable, required
      - `credits` number, double, required
  - `last_request_at` string, date-time, nullable, required
  - `cost_recorded_request_count` integer, required
  - `failed_request_count` integer, required
  - `cold_request_count` integer, required
  - `end_to_end_p50_ms` number, double, nullable, required
  - `end_to_end_p95_ms` number, double, nullable, required
  - `latest_failure` InferenceFailure, required
    - `id` string, uuid, required
    - `created_at` string, date-time, required
    - `error_code` string, required
  - `request_count` integer, required
  - `prompt_tokens` integer, required
  - `completion_tokens` integer, required
  - `total_tokens` integer, required
  - `cost` number, double, nullable, required
  - `cost_this_month` number, double, nullable, required
  - `cost_is_estimate` boolean, required
  - `avg_tokens_per_second` number, double, nullable, required
  - `avg_latency_ms` number, double, nullable, required
  - `latency_p95_ms` number, double, nullable, required
  - `cold_start_ms` number, double, nullable, required
  - `baseline_model` string, nullable, required
  - `baseline_cost` number, double, nullable, required
  - `savings` number, double, nullable, required

---

[API](https://skmtc.dev/overmindlab/apis/overmind-api.md) - [All operations](https://skmtc.dev/overmindlab/apis/overmind-api/llms.txt) - [OpenAPI document](https://skmtc.dev/overmindlab/apis/overmind-api/revisions/0ecfd39e80c6?raw)