GET/api/v1/cost/burn-rate

Live $/hr burn-rate projection for an org

Returns the projected hourly burn rate computed from a trailing window (default 300s) of gateway_proxy_logs. Includes window cost, call count, top cost drivers by (provider, model), and a server-rendered timestamp. Cache-Control: no-store — clients must not cache.

Authentication

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

Parameters

orgId in queryrequired
string
windowSeconds in query
integer

Response

All status codes

200Burn-rate snapshot
400(no description)
401(no description)
429(no description)
500DB_ERROR fetching gateway_proxy_logs

Code samples

cURL

curl -X GET \
  https://evalguard.ai/api/v1/cost/burn-rate \
  -H "Authorization: Bearer $EVALGUARD_API_KEY" \

TypeScript

import { EvalGuard } from "@evalguard/sdk";

const client = new EvalGuard({ apiKey: process.env.EVALGUARD_API_KEY });

const response = await client.request({
  method: "GET",
  path: "/api/v1/cost/burn-rate",
});
console.log(response);

Python

from evalguard import EvalGuard
import os

client = EvalGuard(api_key=os.environ["EVALGUARD_API_KEY"])

response = client.request(method="GET", path="/api/v1/cost/burn-rate")
print(response)

Go

package main

import (
	"context"
	"fmt"
	"os"

	"github.com/evalguard/evalguard-go"
)

func main() {
	client := evalguard.NewClient(os.Getenv("EVALGUARD_API_KEY"))
	resp, err := client.Request(context.Background(), "GET", "/api/v1/cost/burn-rate", nil)
	if err != nil { panic(err) }
	fmt.Println(resp)
}

Errors

400401429500

Other Cost & FinOps endpoints