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

Configure GPU monitoring alerts

Ingests GPU node metrics into `gpu_metrics`. Body: `projectId` (required, 1-200 chars) and `metrics[]` (1-1000 objects); each element may carry `nodeName`, `gpuType`, `utilization`, `memoryUsage`, `temperature`, `costPerHour` and `status` (defaults to `active`), and every row is stamped with the server's `recorded_at`. Returns 201 `{message: '<n> GPU metrics recorded'}`. Sets no alert thresholds — this is the only write path into `gpu_metrics`. Requires the org `admin` role (matching the table's own owner/admin RLS policy, which the API-key path would otherwise bypass) and `gateway:create`; audit-logged; 120 req/min.

Authentication

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

Request body required

Example

{
  "projectId": "string",
  "metrics": [
    {
      "nodeName": "string",
      "gpuType": "string",
      "utilization": 0,
      "memoryUsage": 0,
      "temperature": -999.99,
      "costPerHour": 0,
      "status": "string"
    }
  ]
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "properties": {
        "projectId": {
          "type": "string",
          "minLength": 1,
          "maxLength": 200
        },
        "metrics": {
          "minItems": 1,
          "maxItems": 1000,
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "nodeName": {
                "type": "string",
                "minLength": 1,
                "maxLength": 200
              },
              "gpuType": {
                "nullable": true,
                "type": "string",
                "maxLength": 200
              },
              "utilization": {
                "nullable": true,
                "type": "number",
                "minimum": 0,
                "maximum": 999.99
              },
              "memoryUsage": {
                "nullable": true,
                "type": "number",
                "minimum": 0,
                "maximum": 999.99
              },
              "temperature": {
                "nullable": true,
                "type": "number",
                "minimum": -999.99,
                "maximum": 999.99
              },
              "costPerHour": {
                "nullable": true,
                "type": "number",
                "minimum": 0,
                "maximum": 9999.9999
              },
              "status": {
                "nullable": true,
                "type": "string",
                "maxLength": 50
              }
            },
            "required": [
              "nodeName"
            ],
            "additionalProperties": {}
          }
        }
      },
      "required": [
        "projectId",
        "metrics"
      ],
      "additionalProperties": {}
    }
  }
}

Response

200 example

{
  "success": true
}

All status codes

200Configured.
201Created.
400(no description)
401(no description)
403Forbidden — insufficient role for this operation.
404Not Found — NOT_FOUND.
409Conflict — CONFLICT.
429(no description)
500Internal Server Error — DB_ERROR.

Code samples

cURL

curl -X POST \
  https://evalguard.ai/api/v1/gpu-monitoring \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "projectId": "string", "metrics": [ { "nodeName": "string", "gpuType": "string", "utilization": 0, "memoryUsage": 0, "temperature": -999.99, "costPerHour": 0, "status": "string" } ] }'

TypeScript

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

const res = await fetch("https://evalguard.ai/api/v1/gpu-monitoring", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "projectId": "string",
    "metrics": [
      {
        "nodeName": "string",
        "gpuType": "string",
        "utilization": 0,
        "memoryUsage": 0,
        "temperature": -999.99,
        "costPerHour": 0,
        "status": "string"
      }
    ]
  }),
});
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']}"}
headers["Content-Type"] = "application/json"

response = requests.request(
    "POST",
    "https://evalguard.ai/api/v1/gpu-monitoring",
    headers=headers,
    json={
    "projectId": "string",
    "metrics": [
        {
            "nodeName": "string",
            "gpuType": "string",
            "utilization": 0,
            "memoryUsage": 0,
            "temperature": -999.99,
            "costPerHour": 0,
            "status": "string"
        }
    ]
},
)
print(response.status_code, response.json())

Go

package main

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

func main() {
	body := strings.NewReader(`{"projectId":"string","metrics":[{"nodeName":"string","gpuType":"string","utilization":0,"memoryUsage":0,"temperature":-999.99,"costPerHour":0,"status":"string"}]}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/gpu-monitoring", body)
	req.Header.Set("Authorization", "Bearer "+os.Getenv("EVALGUARD_API_KEY"))
	req.Header.Set("Content-Type", "application/json")
	resp, err := http.DefaultClient.Do(req)
	if err != nil { panic(err) }
	defer resp.Body.Close()
	fmt.Println(resp.Status)
}

Errors

400401403404409429500

Other Monitoring endpoints