Skip to content
GET/api/v1/gpu-monitoring

Get GPU/inference monitoring

Returns self-reported GPU node metrics previously POSTed to this endpoint. `?projectId` is required (400). Reads the 100 most recent `gpu_metrics` rows for the project and returns `{nodes, history, summary}`, where `nodes` is the newest row per `node_name` and the summary is `{totalNodes, activeNodes, avgUtilization, idleNodes (utilization below 10), totalCostPerHour}`. Per-node fields are utilization, memory usage (percent), temperature, cost per hour and status — there is no queue depth or per-request latency, and no provider-level fallback when no rows exist (the response is simply empty). Passing `?view=recommendations` instead replays the same rows through the core GPUMonitor engine and returns `{projectId, periodHours, recommendations}` (shutdown / consolidate / upscale, sorted by estimated savings). 60 req/min.

Authentication

Send Authorization: Bearer YOUR_API_KEY on every request. Generate API keys at /dashboard/settings/api-keys.

Response

200 example

{
  "success": true
}

All status codes

200GPU metrics.
400(no description)
401(no description)
403Forbidden — the credential is valid but lacks the API-key scope, member role, or plan entitlement this operation requires.
429(no description)
500Internal Server Error — an unhandled error was converted to the standard error envelope (INTERNAL_ERROR).

Code samples

cURL

curl -X GET \
  https://evalguard.ai/api/v1/gpu-monitoring \
  -H "Authorization: Bearer $EVALGUARD_API_KEY"

TypeScript

// The TypeScript SDK (@evalguard/sdk) exposes TYPED methods — runEval,
// getEval, runSecurityScan, checkFirewall, … — not a generic request().
// For an arbitrary endpoint, call it directly:

const res = await fetch("https://evalguard.ai/api/v1/gpu-monitoring", {
  method: "GET",
  headers: { Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}` },
});
console.log(res.status, await res.json());

Python

# The Python SDK (pip install evalguardai) exposes TYPED methods on
# EvalGuardClient — run_eval, get_eval, … — not a generic request().
# For an arbitrary endpoint, call it directly:

import os
import requests

headers = {"Authorization": f"Bearer {os.environ['EVALGUARD_API_KEY']}"}

response = requests.request("GET", "https://evalguard.ai/api/v1/gpu-monitoring", headers=headers)
print(response.status_code, response.json())

Go

package main

import (
	"context"
	"fmt"
	"net/http"
	"os"
)

func main() {
	req, _ := http.NewRequestWithContext(context.Background(), "GET", "https://evalguard.ai/api/v1/gpu-monitoring", nil)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

400401403429500

Other Monitoring endpoints