Skip to content
POST/api/v1/monitoring/sla

Create an SLA target

Adds an SLA target. Requires an org — `orgId` as a query param or body field, or an org-pinned `eg_` key (400 MISSING_ORG_ID when none resolves) plus `name`, `modelOrEndpoint`, `metric` and `target`; `metric` must be one of availability, latency_p95, latency_p99, error_rate, throughput. Optional `operator` (defaults to `gte` for availability/throughput, `lte` otherwise), `windowMinutes` (default 60) and `severity` (critical|warning|info, default warning). The target is stamped with the caller's org so the sibling GET and DELETE can only see and remove it. Returns 201. SLA targets live in a process-local in-memory store, not the database: they do not survive a restart and are not shared across server instances.

Authentication

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

Request body required

Example

{
  "name": "string",
  "modelOrEndpoint": "string",
  "metric": "availability",
  "target": 0,
  "operator": "lte",
  "windowMinutes": 60,
  "severity": "warning"
}
Schema
{
  "application/json": {
    "schema": {
      "type": "object",
      "required": [
        "name",
        "modelOrEndpoint",
        "metric",
        "target"
      ],
      "properties": {
        "name": {
          "type": "string"
        },
        "modelOrEndpoint": {
          "type": "string"
        },
        "metric": {
          "type": "string",
          "enum": [
            "availability",
            "latency_p95",
            "latency_p99",
            "error_rate",
            "throughput"
          ]
        },
        "target": {
          "type": "number"
        },
        "operator": {
          "type": "string",
          "enum": [
            "lte",
            "gte"
          ],
          "description": "Defaults to gte for availability/throughput, lte otherwise."
        },
        "windowMinutes": {
          "type": "number",
          "default": 60
        },
        "severity": {
          "type": "string",
          "enum": [
            "critical",
            "warning",
            "info"
          ],
          "default": "warning"
        }
      }
    }
  }
}

Response

201 example

{
  "success": true
}

All status codes

201Created.
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 POST \
  https://evalguard.ai/api/v1/monitoring/sla \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "name": "string", "modelOrEndpoint": "string", "metric": "availability", "target": 0, "operator": "lte", "windowMinutes": 60, "severity": "warning" }'

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/monitoring/sla", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.EVALGUARD_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "name": "string",
    "modelOrEndpoint": "string",
    "metric": "availability",
    "target": 0,
    "operator": "lte",
    "windowMinutes": 60,
    "severity": "warning"
  }),
});
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/monitoring/sla",
    headers=headers,
    json={
    "name": "string",
    "modelOrEndpoint": "string",
    "metric": "availability",
    "target": 0,
    "operator": "lte",
    "windowMinutes": 60,
    "severity": "warning"
},
)
print(response.status_code, response.json())

Go

package main

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

func main() {
	body := strings.NewReader(`{"name":"string","modelOrEndpoint":"string","metric":"availability","target":0,"operator":"lte","windowMinutes":60,"severity":"warning"}`)
	req, _ := http.NewRequestWithContext(context.Background(), "POST", "https://evalguard.ai/api/v1/monitoring/sla", 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

400401403429500

Other Monitoring endpoints