Deployments
Get deployment metrics
Returns per-node GPU/CPU/memory utilization and Knative queue-proxy request rate / concurrency / latency for the trainer pods. The sampler half of a Loops deployment is an OracleVersion and uses the existing model-metrics endpoint.
POST
/
v1
/
loops
/
deployments
/
{deployment_id}
/
metrics
cURL
curl --request POST \
--url https://api.baseten.co/v1/loops/deployments/{deployment_id}/metrics \
--header "Authorization: Bearer $BASETEN_API_KEY" \
--data '{
"end_epoch_millis": null,
"start_epoch_millis": null,
"step_seconds": null,
"time_divisor_seconds": null
}'import requests
import os
API_KEY = os.environ.get("BASETEN_API_KEY", "<YOUR_API_KEY>")
url = "https://api.baseten.co/v1/loops/deployments/{deployment_id}/metrics"
headers = {"Authorization": f"Bearer {API_KEY}"}
response = requests.request(
"POST",
url,
headers=headers,
json={'end_epoch_millis': None, 'start_epoch_millis': None, 'step_seconds': None, 'time_divisor_seconds': None}
)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
end_epoch_millis: 123,
start_epoch_millis: 123,
step_seconds: 123,
time_divisor_seconds: 123
})
};
fetch('https://api.baseten.co/v1/loops/deployments/{deployment_id}/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/loops/deployments/{deployment_id}/metrics",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'end_epoch_millis' => 123,
'start_epoch_millis' => 123,
'step_seconds' => 123,
'time_divisor_seconds' => 123
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.baseten.co/v1/loops/deployments/{deployment_id}/metrics"
payload := strings.NewReader("{\n \"end_epoch_millis\": 123,\n \"start_epoch_millis\": 123,\n \"step_seconds\": 123,\n \"time_divisor_seconds\": 123\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.baseten.co/v1/loops/deployments/{deployment_id}/metrics")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"end_epoch_millis\": 123,\n \"start_epoch_millis\": 123,\n \"step_seconds\": 123,\n \"time_divisor_seconds\": 123\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.baseten.co/v1/loops/deployments/{deployment_id}/metrics")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"end_epoch_millis\": 123,\n \"start_epoch_millis\": 123,\n \"step_seconds\": 123,\n \"time_divisor_seconds\": 123\n}"
response = http.request(request)
puts response.read_body{
"deployment_id": "<string>",
"metrics": {
"inference_volume": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"concurrent_requests": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"response_time_stats": [
{
"timestamp": "2023-11-07T05:31:56Z",
"p50": 123,
"p95": 123,
"p99": 123
}
],
"inference_volume_by_status": [
{
"timestamp": "2023-11-07T05:31:56Z",
"status_2xx": 123,
"status_4xx": 123,
"status_5xx": 123
}
],
"gpu_memory_usage_bytes": {},
"gpu_utilization": {},
"cpu_usage": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"cpu_memory_usage_bytes": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"ephemeral_storage": {
"usage_bytes": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"utilization": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
]
},
"per_node_metrics": [
{
"node_id": "<string>",
"gpu_memory_usage_bytes": {},
"gpu_utilization": {},
"cpu_usage": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"cpu_memory_usage_bytes": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"ephemeral_storage": {
"usage_bytes": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"utilization": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
]
}
}
]
}
}Authorizations
Send Authorization: Bearer <api_key>. The legacy Authorization: Api-Key <api_key> scheme is also accepted.
Path Parameters
Body
application/json
Time-range request for trainer deployment metrics.
Epoch millis to end fetching metrics.
Epoch millis to start fetching metrics.
Resolution of the returned series, in seconds. When omitted, a step is derived from the time range so large windows return fewer points.
Unit of time for request-volume metrics, in seconds (e.g. 60 for requests/minute). Defaults to per-second.
Was this page helpful?
Previous
Get deployment logsFetches logs from the trainer pods of a Loops deployment. Visible to any member of the deployment's team.
Next
⌘I
cURL
curl --request POST \
--url https://api.baseten.co/v1/loops/deployments/{deployment_id}/metrics \
--header "Authorization: Bearer $BASETEN_API_KEY" \
--data '{
"end_epoch_millis": null,
"start_epoch_millis": null,
"step_seconds": null,
"time_divisor_seconds": null
}'import requests
import os
API_KEY = os.environ.get("BASETEN_API_KEY", "<YOUR_API_KEY>")
url = "https://api.baseten.co/v1/loops/deployments/{deployment_id}/metrics"
headers = {"Authorization": f"Bearer {API_KEY}"}
response = requests.request(
"POST",
url,
headers=headers,
json={'end_epoch_millis': None, 'start_epoch_millis': None, 'step_seconds': None, 'time_divisor_seconds': None}
)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
end_epoch_millis: 123,
start_epoch_millis: 123,
step_seconds: 123,
time_divisor_seconds: 123
})
};
fetch('https://api.baseten.co/v1/loops/deployments/{deployment_id}/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/loops/deployments/{deployment_id}/metrics",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'end_epoch_millis' => 123,
'start_epoch_millis' => 123,
'step_seconds' => 123,
'time_divisor_seconds' => 123
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.baseten.co/v1/loops/deployments/{deployment_id}/metrics"
payload := strings.NewReader("{\n \"end_epoch_millis\": 123,\n \"start_epoch_millis\": 123,\n \"step_seconds\": 123,\n \"time_divisor_seconds\": 123\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://api.baseten.co/v1/loops/deployments/{deployment_id}/metrics")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"end_epoch_millis\": 123,\n \"start_epoch_millis\": 123,\n \"step_seconds\": 123,\n \"time_divisor_seconds\": 123\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.baseten.co/v1/loops/deployments/{deployment_id}/metrics")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"end_epoch_millis\": 123,\n \"start_epoch_millis\": 123,\n \"step_seconds\": 123,\n \"time_divisor_seconds\": 123\n}"
response = http.request(request)
puts response.read_body{
"deployment_id": "<string>",
"metrics": {
"inference_volume": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"concurrent_requests": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"response_time_stats": [
{
"timestamp": "2023-11-07T05:31:56Z",
"p50": 123,
"p95": 123,
"p99": 123
}
],
"inference_volume_by_status": [
{
"timestamp": "2023-11-07T05:31:56Z",
"status_2xx": 123,
"status_4xx": 123,
"status_5xx": 123
}
],
"gpu_memory_usage_bytes": {},
"gpu_utilization": {},
"cpu_usage": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"cpu_memory_usage_bytes": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"ephemeral_storage": {
"usage_bytes": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"utilization": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
]
},
"per_node_metrics": [
{
"node_id": "<string>",
"gpu_memory_usage_bytes": {},
"gpu_utilization": {},
"cpu_usage": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"cpu_memory_usage_bytes": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"ephemeral_storage": {
"usage_bytes": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
],
"utilization": [
{
"value": 123,
"timestamp": "2023-11-07T05:31:56Z"
}
]
}
}
]
}
}