GPUs

List accelerators

Returns items and a total for the accelerators held by the tenant selected by the X-CostGraph-Tenant-ID header. An accelerator that has reported gets its own item carrying its utilisation band, its 24h, 7d and 30d utilisation and memory, its hourly and monthly cost where the catalog prices it, and its MIG partitions with the ones that ran no compute marked idle. The accelerators on a machine that have not reported are counted in one further item per machine, with a null gpu_uuid, unreported_card_count set, and every measured field null rather than zero. A machine that reports its accelerators through the host agent rather than through Kubernetes gets its own item in the same shape, counted in unreported_card_count with every measured field null, since the agent reports what the hardware is and never how busy it was; such a machine is listed separately from any Kubernetes node and is never merged with one. model_source names what answered for the model, and reported_by names which path answered for the accelerator: operator for a card reporting through Kubernetes, agent for one the host agent inventoried, and catalog for cards the machine is priced for but none has reported. placement says where the accelerator sits and carries the ids a caller links on: placement.instance_id always, and placement.cluster_id, placement.node_id and placement.node_name where the machine is a Kubernetes node we hold, which is also what makes placement.kind workload rather than instance. placement.namespace names the namespace of the workload that asked for the accelerator, and stays null where no workload on that node asks for one or where more than one namespace does. gpu_availability states every signal the card could report, read from the measurements stored against it: supported where it was measured, capacity_unknown where it was measured but nothing expresses it as a percentage, unsupported where the card reports other signals but not this one, and no_data where the card reported nothing at all; no signal is ever omitted or returned as zero. A report whose 7-day or 30-day window has not been computed carries window_7d or window_30d as null rather than as a zero measurement. cost carries the currency every amount is in, the hourly and projected monthly rate the catalog prices the card at, and mtd_reason saying why mtd and change_percent are null; spend to date is billed for the whole machine, so it is never attributed to one accelerator and never rendered as zero. utilization_sparkline and memory_utilization_sparkline each carry the trailing 24 hours as 12 fixed-width 2 hour buckets, oldest first, each holding the highest percentage the card reached in that bucket; a bucket the card took no sample in is null, a card that has never reported carries twelve nulls rather than zeros, and a card carved into MIG partitions is read once for the whole card rather than once per partition. total_count is the filtered count before paging.

GET

api

tenant

gpus

List accelerators

curl --request GET \
  --url https://api.costgraph.ai/api/v1/tenant/gpus \
  --header 'Authorization: <api-key>' \
  --header 'X-CostGraph-Tenant-ID: <x-costgraph-tenant-id>'

import requests

url = "https://api.costgraph.ai/api/v1/tenant/gpus"

headers = {
    "X-CostGraph-Tenant-ID": "<x-costgraph-tenant-id>",
    "Authorization": "<api-key>"
}

response = requests.get(url, headers=headers)

print(response.text)

const options = {
  method: 'GET',
  headers: {'X-CostGraph-Tenant-ID': '<x-costgraph-tenant-id>', Authorization: '<api-key>'}
};

fetch('https://api.costgraph.ai/api/v1/tenant/gpus', 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.costgraph.ai/api/v1/tenant/gpus",
  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: <api-key>",
    "X-CostGraph-Tenant-ID: <x-costgraph-tenant-id>"
  ],
]);

$response = curl_exec($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.costgraph.ai/api/v1/tenant/gpus"

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

	req.Header.Add("X-CostGraph-Tenant-ID", "<x-costgraph-tenant-id>")
	req.Header.Add("Authorization", "<api-key>")

	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.costgraph.ai/api/v1/tenant/gpus")
  .header("X-CostGraph-Tenant-ID", "<x-costgraph-tenant-id>")
  .header("Authorization", "<api-key>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.costgraph.ai/api/v1/tenant/gpus")

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

request = Net::HTTP::Get.new(url)
request["X-CostGraph-Tenant-ID"] = '<x-costgraph-tenant-id>'
request["Authorization"] = '<api-key>'

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

{
  "message": "some message",
  "status": "success",
  "data": {
    "items": [
      {
        "memory_utilization_sparkline": [
          123
        ],
        "utilization_sparkline": [
          123
        ],
        "action": "<string>",
        "cost": {
          "change_percent": 123,
          "currency": "<string>",
          "hourly_rate": 123,
          "mtd": 123,
          "mtd_reason": "<string>",
          "projected_monthly_spend": 123
        },
        "cost_per_hour": 123,
        "data_age_hours": 123,
        "data_quality_state": "<string>",
        "gpu_count": 123,
        "gpu_index": 123,
        "gpu_uuid": "<string>",
        "idle_partition_count": 123,
        "instance_id": "<string>",
        "last_reported_at": "<string>",
        "memory_used_p95": 123,
        "memory_used_p95_30d": 123,
        "memory_used_p95_7d": 123,
        "memory_utilization_percent": 123,
        "mig_enabled": true,
        "model": "<string>",
        "model_source": "<string>",
        "partition_count": 123,
        "partitions": [
          {
            "idle": true,
            "mig_instance_id": "<string>",
            "mig_profile": "<string>",
            "utilization_band": "<string>",
            "utilization_p95": 123
          }
        ],
        "placement": {
          "cluster": "<string>",
          "cluster_id": "<string>",
          "instance_id": "<string>",
          "kind": "<string>",
          "name": "<string>",
          "namespace": "<string>",
          "node_id": "<string>",
          "node_name": "<string>"
        },
        "power_mean_watts": 123,
        "provider": "<string>",
        "region": "<string>",
        "reported_by": "<string>",
        "unreported_card_count": 123,
        "urgency": "<string>",
        "utilization_band": "<string>",
        "utilization_p95_30d": 123,
        "utilization_p95_7d": 123,
        "utilization_percent": 123,
        "vendor": "<string>"
      }
    ],
    "limit": 123,
    "offset": 123,
    "total_count": 123
  }
}

{
  "message": "some message",
  "status": "error"
}

{
  "message": "some message",
  "status": "error"
}

{
  "message": "some message",
  "status": "error"
}

{
  "message": "some message",
  "status": "error"
}

Authorizations

Authorization

string

header

required

Enter "Bearer {token}"

Headers

X-CostGraph-Tenant-ID

string

required

Tenant ID

Query Parameters

model

string

Filter to one accelerator model

utilization_band

string

Filter to one utilisation band

instance_id

string

Filter to accelerators held by one instance

cluster_id

string

Filter to accelerators on the machines of one Kubernetes cluster

provider

string[]

Filter to one or more cloud providers

placement_kind

string[]

Filter to where the accelerator sits: instance or workload

string

Case-insensitive match over the accelerator model and the name of the machine holding it

partitioned

boolean

Filter to partitioned or whole cards

window

string

Only accelerators that reported within this window, as a duration such as 24h, 7d or 30d. Omit to include ones that stopped reporting.

limit

integer

Number of rows to return (default 50, max 200)

offset

integer

Rows to skip

Response

message

string

required

Example:

"some message"

status

string

required

Example:

"success"

data

object

Show child attributes

List accelerators

curl --request GET \
  --url https://api.costgraph.ai/api/v1/tenant/gpus \
  --header 'Authorization: <api-key>' \
  --header 'X-CostGraph-Tenant-ID: <x-costgraph-tenant-id>'

import requests

url = "https://api.costgraph.ai/api/v1/tenant/gpus"

headers = {
    "X-CostGraph-Tenant-ID": "<x-costgraph-tenant-id>",
    "Authorization": "<api-key>"
}

response = requests.get(url, headers=headers)

print(response.text)

const options = {
  method: 'GET',
  headers: {'X-CostGraph-Tenant-ID': '<x-costgraph-tenant-id>', Authorization: '<api-key>'}
};

fetch('https://api.costgraph.ai/api/v1/tenant/gpus', 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.costgraph.ai/api/v1/tenant/gpus",
  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: <api-key>",
    "X-CostGraph-Tenant-ID: <x-costgraph-tenant-id>"
  ],
]);

$response = curl_exec($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.costgraph.ai/api/v1/tenant/gpus"

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

	req.Header.Add("X-CostGraph-Tenant-ID", "<x-costgraph-tenant-id>")
	req.Header.Add("Authorization", "<api-key>")

	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.costgraph.ai/api/v1/tenant/gpus")
  .header("X-CostGraph-Tenant-ID", "<x-costgraph-tenant-id>")
  .header("Authorization", "<api-key>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.costgraph.ai/api/v1/tenant/gpus")

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

request = Net::HTTP::Get.new(url)
request["X-CostGraph-Tenant-ID"] = '<x-costgraph-tenant-id>'
request["Authorization"] = '<api-key>'

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

{
  "message": "some message",
  "status": "success",
  "data": {
    "items": [
      {
        "memory_utilization_sparkline": [
          123
        ],
        "utilization_sparkline": [
          123
        ],
        "action": "<string>",
        "cost": {
          "change_percent": 123,
          "currency": "<string>",
          "hourly_rate": 123,
          "mtd": 123,
          "mtd_reason": "<string>",
          "projected_monthly_spend": 123
        },
        "cost_per_hour": 123,
        "data_age_hours": 123,
        "data_quality_state": "<string>",
        "gpu_count": 123,
        "gpu_index": 123,
        "gpu_uuid": "<string>",
        "idle_partition_count": 123,
        "instance_id": "<string>",
        "last_reported_at": "<string>",
        "memory_used_p95": 123,
        "memory_used_p95_30d": 123,
        "memory_used_p95_7d": 123,
        "memory_utilization_percent": 123,
        "mig_enabled": true,
        "model": "<string>",
        "model_source": "<string>",
        "partition_count": 123,
        "partitions": [
          {
            "idle": true,
            "mig_instance_id": "<string>",
            "mig_profile": "<string>",
            "utilization_band": "<string>",
            "utilization_p95": 123
          }
        ],
        "placement": {
          "cluster": "<string>",
          "cluster_id": "<string>",
          "instance_id": "<string>",
          "kind": "<string>",
          "name": "<string>",
          "namespace": "<string>",
          "node_id": "<string>",
          "node_name": "<string>"
        },
        "power_mean_watts": 123,
        "provider": "<string>",
        "region": "<string>",
        "reported_by": "<string>",
        "unreported_card_count": 123,
        "urgency": "<string>",
        "utilization_band": "<string>",
        "utilization_p95_30d": 123,
        "utilization_p95_7d": 123,
        "utilization_percent": 123,
        "vendor": "<string>"
      }
    ],
    "limit": 123,
    "offset": 123,
    "total_count": 123
  }
}

{
  "message": "some message",
  "status": "error"
}

{
  "message": "some message",
  "status": "error"
}

{
  "message": "some message",
  "status": "error"
}

{
  "message": "some message",
  "status": "error"
}

Getting started

Endpoints

List accelerators

Authorizations

Headers

Query Parameters

Response