Get environment metrics

Gets metrics aggregated across every deployment that was active on the environment in the given time range. In series mode the window is split at each promotion so that every point reflects the deployment(s) serving the environment at that time.

GET /v1/models/{model_id}/environments/{env_name}/metrics

cURL

cURL

curl --request GET \
--url https://api.baseten.co/v1/models/{model_id}/environments/{env_name}/metrics \
--header "Authorization: Bearer $BASETEN_API_KEY"

import requests
import os
API_KEY = os.environ.get("BASETEN_API_KEY", "<YOUR_API_KEY>")
url = "https://api.baseten.co/v1/models/{model_id}/environments/{env_name}/metrics"

headers = {"Authorization": f"Bearer {API_KEY}"}

response = requests.request(
    "GET",
    url,
    headers=headers,
    json={}
)

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.baseten.co/v1/models/{model_id}/environments/{env_name}/metrics', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.baseten.co/v1/models/{model_id}/environments/{env_name}/metrics",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.baseten.co/v1/models/{model_id}/environments/{env_name}/metrics"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.get("https://api.baseten.co/v1/models/{model_id}/environments/{env_name}/metrics")
  .header("Authorization", "Bearer <token>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.baseten.co/v1/models/{model_id}/environments/{env_name}/metrics")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

response = http.request(request)
puts response.read_body

200

{
  "start_epoch_millis": 123,
  "end_epoch_millis": 123,
  "step_seconds": 123,
  "metric_descriptors": [
    {
      "name": "<string>",
      "label_sets": [
        {}
      ]
    }
  ],
  "metric_values": [
    {
      "start_epoch_millis": 123,
      "values": [
        [
          123
        ]
      ]
    }
  ]
}

This endpoint is in beta. The request and response structure may change before it’s generally available.

Related guide: Pull logs and metrics.

Authorizations

Authorization · string · header · required

Send Authorization: Bearer <api_key>. The legacy Authorization: Api-Key <api_key> scheme is also accepted.

Path Parameters

model_id · string · required

env_name · string · required

Query Parameters

mode · enum<string> · default: CURRENT

'CURRENT': a single instantaneous snapshot at now; start/end must be omitted. 'SUMMARY': a single value set aggregating the whole window. 'SERIES': evenly-spaced value sets across the window, with the step derived from the window duration. How metric values are aggregated over the request.

Available options: CURRENT, SUMMARY, SERIES

start_epoch_millis · integer | null

Epoch millis timestamp to start fetching metrics. Defaults to one hour before the end.

end_epoch_millis · integer | null

Epoch millis timestamp to end fetching metrics. Defaults to the current time. The window between start and end must not exceed 7 days.

metrics · string[]

Names of the metrics to return; see https://docs.baseten.co/observability/export-metrics/supported-metrics for the available names. When omitted, a default set is returned: baseten_replicas_active, baseten_inference_requests_total, and baseten_end_to_end_response_time_seconds. Unknown names are rejected; valid names that do not apply are omitted from the response.

Response

200 - application/json

Model metrics over a time window, index-mapped: metric descriptors appear once in metric_descriptors; each value set's values are aligned to that order.

start_epoch_millis · integer · required

Start of the returned window.

end_epoch_millis · integer · required

End of the returned window.

mode · enum<string> · required

The aggregation mode used.

Available options: CURRENT, SUMMARY, SERIES

step_seconds · integer | null · required

Seconds per step; populated only in SERIES mode, null otherwise.

metric_descriptors · ModelMetricDescriptorV1 · object[] · required

Descriptors for each metric; position defines the values index.

Show child attributes

metric_values · ModelMetricValueSetV1 · object[] · required

Metric values per time step covering the window. In summary mode this always contains exactly one value set spanning the whole window.

Show child attributes