Skip to content
GET/api/v1/gateway/canary

List active canary deployments

Returns the status of the ONE active canary for a project. Requires `?projectId` (400 if missing) and verifies org membership through it. Answers { projectId, active } and, when a canary is running, { config (currentModel, canaryModel, trafficPercent, minSamples, successThreshold, autoPromote), metrics (currentSuccess, currentTotal, canarySuccess, canaryTotal, startedAt), canarySuccessRate, currentSuccessRate } — success/error rates only; no latency or cost-delta figures are tracked. A canary routes `trafficPercent` of gateway traffic to the candidate model and the rest to the stable one. State is held in the serving process's memory, not the database, so it does not survive a restart and is not shared across instances. 120 req/min.

Authentication

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

Parameters

projectId in queryrequired
string

Response

200 example

{
  "success": true
}

All status codes

200Active canaries with per-canary status.
400Invalid params.
401Unauthorized — no valid credential was presented (AUTH_REQUIRED).
403Cross-tenant denial.
429Too Many Requests — the per-key or per-organization rate limit was exceeded. Honour the Retry-After header.
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/gateway/canary \
  -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/gateway/canary", {
  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/gateway/canary", 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/gateway/canary", 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 Gateway endpoints